Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 349 results for author: <span class="mathjax">Sun, Y</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/eess" aria-role="search"> Searching in archive <strong>eess</strong>. <a href="/search/?searchtype=author&query=Sun%2C+Y">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Sun, Y"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Sun%2C+Y&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Sun, Y"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=300" class="pagination-link " aria-label="Page 7" aria-current="page">7 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.03501">arXiv:2502.03501</a> <span> [<a href="https://arxiv.org/pdf/2502.03501">pdf</a>, <a href="https://arxiv.org/format/2502.03501">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Proxy Prompt: Endowing SAM and SAM 2 with Auto-Interactive-Prompt for Medical Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xinyi%2C+W">Wang Xinyi</a>, <a href="/search/eess?searchtype=author&query=Hongyu%2C+K">Kang Hongyu</a>, <a href="/search/eess?searchtype=author&query=Peishan%2C+W">Wei Peishan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shuai Li</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yu Sun</a>, <a href="/search/eess?searchtype=author&query=Lam%2C+S+K">Sai Kit Lam</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+Y">Yongping Zheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.03501v1-abstract-short" style="display: inline;"> In this paper, we aim to address the unmet demand for automated prompting and enhanced human-model interactions of SAM and SAM2 for the sake of promoting their widespread clinical adoption. Specifically, we propose Proxy Prompt (PP), auto-generated by leveraging non-target data with a pre-annotated mask. We devise a novel 3-step context-selection strategy for adaptively selecting the most represen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03501v1-abstract-full').style.display = 'inline'; document.getElementById('2502.03501v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.03501v1-abstract-full" style="display: none;"> In this paper, we aim to address the unmet demand for automated prompting and enhanced human-model interactions of SAM and SAM2 for the sake of promoting their widespread clinical adoption. Specifically, we propose Proxy Prompt (PP), auto-generated by leveraging non-target data with a pre-annotated mask. We devise a novel 3-step context-selection strategy for adaptively selecting the most representative contextual information from non-target data via vision mamba and selective maps, empowering the guiding capability of non-target image-mask pairs for segmentation on target image/video data. To reinforce human-model interactions in PP, we further propose a contextual colorization module via a dual-reverse cross-attention to enhance interactions between target features and contextual-embedding with amplifying distinctive features of user-defined object(s). Via extensive evaluations, our method achieves state-of-the-art performance on four public datasets and yields comparable results with fully-trained models, even when trained with only 16 image masks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03501v1-abstract-full').style.display = 'none'; document.getElementById('2502.03501v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.03132">arXiv:2502.03132</a> <span> [<a href="https://arxiv.org/pdf/2502.03132">pdf</a>, <a href="https://arxiv.org/format/2502.03132">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> SPARK: A Modular Benchmark for Humanoid Robot Safety </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifan Sun</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+R">Rui Chen</a>, <a href="/search/eess?searchtype=author&query=Yun%2C+K+S">Kai S. Yun</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+Y">Yikuan Fang</a>, <a href="/search/eess?searchtype=author&query=Jung%2C+S">Sebin Jung</a>, <a href="/search/eess?searchtype=author&query=Li%2C+F">Feihan Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+B">Bowei Li</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+W">Weiye Zhao</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+C">Changliu Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.03132v1-abstract-short" style="display: inline;"> This paper introduces the Safe Protective and Assistive Robot Kit (SPARK), a comprehensive benchmark designed to ensure safety in humanoid autonomy and teleoperation. Humanoid robots pose significant safety risks due to their physical capabilities of interacting with complex environments. The physical structures of humanoid robots further add complexity to the design of general safety solutions. T… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03132v1-abstract-full').style.display = 'inline'; document.getElementById('2502.03132v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.03132v1-abstract-full" style="display: none;"> This paper introduces the Safe Protective and Assistive Robot Kit (SPARK), a comprehensive benchmark designed to ensure safety in humanoid autonomy and teleoperation. Humanoid robots pose significant safety risks due to their physical capabilities of interacting with complex environments. The physical structures of humanoid robots further add complexity to the design of general safety solutions. To facilitate the safe deployment of complex robot systems, SPARK can be used as a toolbox that comes with state-of-the-art safe control algorithms in a modular and composable robot control framework. Users can easily configure safety criteria and sensitivity levels to optimize the balance between safety and performance. To accelerate humanoid safety research and development, SPARK provides a simulation benchmark that compares safety approaches in a variety of environments, tasks, and robot models. Furthermore, SPARK allows quick deployment of synthesized safe controllers on real robots. For hardware deployment, SPARK supports Apple Vision Pro (AVP) or a Motion Capture System as external sensors, while also offering interfaces for seamless integration with alternative hardware setups. This paper demonstrates SPARK's capability with both simulation experiments and case studies with a Unitree G1 humanoid robot. Leveraging these advantages of SPARK, users and researchers can significantly improve the safety of their humanoid systems as well as accelerate relevant research. The open-source code is available at https://github.com/intelligent-control-lab/spark. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03132v1-abstract-full').style.display = 'none'; document.getElementById('2502.03132v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.18350">arXiv:2501.18350</a> <span> [<a href="https://arxiv.org/pdf/2501.18350">pdf</a>, <a href="https://arxiv.org/format/2501.18350">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Joint Power and Spectrum Orchestration for D2D Semantic Communication Underlying Energy-Efficient Cellular Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xia%2C+L">Le Xia</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yao Sun</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+H">Haijian Sun</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+R+Q">Rose Qingyang Hu</a>, <a href="/search/eess?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/eess?searchtype=author&query=Imran%2C+M+A">Muhammad Ali Imran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.18350v1-abstract-short" style="display: inline;"> Semantic communication (SemCom) has been recently deemed a promising next-generation wireless technique to enable efficient spectrum savings and information exchanges, thus naturally introducing a novel and practical network paradigm where cellular and device-to-device (D2D) SemCom approaches coexist. Nevertheless, the involved wireless resource management becomes complicated and challenging due t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18350v1-abstract-full').style.display = 'inline'; document.getElementById('2501.18350v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18350v1-abstract-full" style="display: none;"> Semantic communication (SemCom) has been recently deemed a promising next-generation wireless technique to enable efficient spectrum savings and information exchanges, thus naturally introducing a novel and practical network paradigm where cellular and device-to-device (D2D) SemCom approaches coexist. Nevertheless, the involved wireless resource management becomes complicated and challenging due to the unique semantic performance measurements and energy-consuming semantic coding mechanism. To this end, this paper jointly investigates power control and spectrum reuse problems for energy-efficient D2D SemCom cellular networks. Concretely, we first model the user preference-aware semantic triplet transmission and leverage a novel metric of semantic value to identify the semantic information importance conveyed in SemCom. Then, we define the additional power consumption from semantic encoding in conjunction with basic power amplifier dissipation to derive the overall system energy efficiency (semantics/Joule). Next, we formulate an energy efficiency maximization problem for joint power and spectrum allocation subject to several SemCom-related and practical constraints. Afterward, we propose an optimal resource management solution by employing the fractional-to-subtractive problem transformation and decomposition while developing a three-stage method with theoretical analysis of its optimality guarantee and computational complexity. Numerical results demonstrate the adequate performance superiority of our proposed solution compared with different benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18350v1-abstract-full').style.display = 'none'; document.getElementById('2501.18350v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been submitted to IEEE Transactions on Wireless Communications for peer review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.17876">arXiv:2501.17876</a> <span> [<a href="https://arxiv.org/pdf/2501.17876">pdf</a>, <a href="https://arxiv.org/format/2501.17876">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Mo%2C+H">Hao Mo</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yaping Sun</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+S">Shumin Yao</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+H">Hao Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhiyong Chen</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+X">Xiaodong Xu</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+N">Nan Ma</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+S">Shuguang Cui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.17876v2-abstract-short" style="display: inline;"> Score-based diffusion models represent a significant variant within the diffusion model family and have seen extensive application in the increasingly popular domain of generative tasks. Recent investigations have explored the denoising potential of diffusion models in semantic communications. However, in previous paradigms, noise distortion in the diffusion process does not match precisely with d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.17876v2-abstract-full').style.display = 'inline'; document.getElementById('2501.17876v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.17876v2-abstract-full" style="display: none;"> Score-based diffusion models represent a significant variant within the diffusion model family and have seen extensive application in the increasingly popular domain of generative tasks. Recent investigations have explored the denoising potential of diffusion models in semantic communications. However, in previous paradigms, noise distortion in the diffusion process does not match precisely with digital channel noise characteristics. In this work, we introduce the Score-Based Channel Denoising Model (SCDM) for Digital Semantic Communications (DSC). SCDM views the distortion of constellation symbol sequences in digital transmission as a score-based forward diffusion process. We design a tailored forward noise corruption to align digital channel noise properties in the training phase. During the inference stage, the well-trained SCDM can effectively denoise received semantic symbols under various SNR conditions, reducing the difficulty for the semantic decoder in extracting semantic information from the received noisy symbols and thereby enhancing the robustness of the reconstructed semantic information. Experimental results show that SCDM outperforms the baseline model in PSNR, SSIM, and MSE metrics, particularly at low SNR levels. Moreover, SCDM reduces storage requirements by a factor of 7.8. This efficiency in storage, combined with its robust denoising capability, makes SCDM a practical solution for DSC across diverse channel conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.17876v2-abstract-full').style.display = 'none'; document.getElementById('2501.17876v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.15368">arXiv:2501.15368</a> <span> [<a href="https://arxiv.org/pdf/2501.15368">pdf</a>, <a href="https://arxiv.org/format/2501.15368">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Baichuan-Omni-1.5 Technical Report </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yadong Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+J">Jun Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+T">Tao Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+T">Tao Zhang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+S">Song Chen</a>, <a href="/search/eess?searchtype=author&query=Li%2C+T">Tianpeng Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zehuan Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Lijun Liu</a>, <a href="/search/eess?searchtype=author&query=Ming%2C+L">Lingfeng Ming</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+G">Guosheng Dong</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+D">Da Pan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chong Li</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+Y">Yuanbo Fang</a>, <a href="/search/eess?searchtype=author&query=Kuang%2C+D">Dongdong Kuang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+M">Mingrui Wang</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+C">Chenglin Zhu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Youwei Zhang</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+H">Hongyu Guo</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+F">Fengyu Zhang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yuran Wang</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+B">Bowen Ding</a>, <a href="/search/eess?searchtype=author&query=Song%2C+W">Wei Song</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xu Li</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+Y">Yuqi Huo</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+Z">Zheng Liang</a> , et al. (68 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.15368v1-abstract-short" style="display: inline;"> We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pip… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15368v1-abstract-full').style.display = 'inline'; document.getElementById('2501.15368v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.15368v1-abstract-full" style="display: none;"> We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data (text, audio, and vision). Second, an audio-tokenizer (Baichuan-Audio-Tokenizer) has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM. Lastly, we designed a multi-stage training strategy that progressively integrates multimodal alignment and multitask fine-tuning, ensuring effective synergy across all modalities. Baichuan-Omni-1.5 leads contemporary models (including GPT4o-mini and MiniCPM-o 2.6) in terms of comprehensive omni-modal capabilities. Notably, it achieves results comparable to leading models such as Qwen2-VL-72B across various multimodal medical benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15368v1-abstract-full').style.display = 'none'; document.getElementById('2501.15368v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.15206">arXiv:2501.15206</a> <span> [<a href="https://arxiv.org/pdf/2501.15206">pdf</a>, <a href="https://arxiv.org/ps/2501.15206">ps</a>, <a href="https://arxiv.org/format/2501.15206">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Applied Physics">physics.app-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Disordered Systems and Neural Networks">cond-mat.dis-nn</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Engineering-Oriented Design of Drift-Resilient MTJ Random Number Generator via Hybrid Control Strategies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Ran Zhang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+C">Caihua Wan</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yingqian Xu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiaohan Li</a>, <a href="/search/eess?searchtype=author&query=Hoffmann%2C+R">Raik Hoffmann</a>, <a href="/search/eess?searchtype=author&query=Hindenberg%2C+M">Meike Hindenberg</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shiqiang Liu</a>, <a href="/search/eess?searchtype=author&query=Kong%2C+D">Dehao Kong</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+S">Shilong Xiong</a>, <a href="/search/eess?searchtype=author&query=He%2C+S">Shikun He</a>, <a href="/search/eess?searchtype=author&query=Vardar%2C+A">Alptekin Vardar</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+Q">Qiang Dai</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+J">Junlu Gong</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yihui Sun</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+Z">Zejie Zheng</a>, <a href="/search/eess?searchtype=author&query=K%C3%A4mpfe%2C+T">Thomas K盲mpfe</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+G">Guoqiang Yu</a>, <a href="/search/eess?searchtype=author&query=Han%2C+X">Xiufeng Han</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.15206v1-abstract-short" style="display: inline;"> In the quest for secure and reliable random number generation, Magnetic Tunnel Junctions (MTJs) have emerged as a promising technology due to their unique ability to exploit the stochastic nature of magnetization switching. This paper presents an engineering-oriented design of a drift-resilient MTJ-based True Random Number Generator (TRNG) utilizing a hybrid control strategy. We address the critic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15206v1-abstract-full').style.display = 'inline'; document.getElementById('2501.15206v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.15206v1-abstract-full" style="display: none;"> In the quest for secure and reliable random number generation, Magnetic Tunnel Junctions (MTJs) have emerged as a promising technology due to their unique ability to exploit the stochastic nature of magnetization switching. This paper presents an engineering-oriented design of a drift-resilient MTJ-based True Random Number Generator (TRNG) utilizing a hybrid control strategy. We address the critical issue of switching probability drift, which can compromise the randomness and bias the output of MTJ-based TRNGs. Our approach combines a self-stabilization strategy, which dynamically adjusts the driving voltage based on real-time feedback, with pulse width modulation to enhance control over the switching probability. Through comprehensive experimental and simulation results, we demonstrate significant improvements in the stability, uniformity, and quality of the random numbers generated. The proposed system offers flexibility and adaptability for diverse applications, making it a reliable solution for high-quality randomness in cryptography, secure communications, and beyond. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15206v1-abstract-full').style.display = 'none'; document.getElementById('2501.15206v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.11586">arXiv:2501.11586</a> <span> [<a href="https://arxiv.org/pdf/2501.11586">pdf</a>, <a href="https://arxiv.org/format/2501.11586">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Compressibility Analysis for the differentiable shift-variant Filtered Backprojection Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ye%2C+C">Chengze Ye</a>, <a href="/search/eess?searchtype=author&query=Schneider%2C+L">Linda-Sophie Schneider</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yipeng Sun</a>, <a href="/search/eess?searchtype=author&query=Thies%2C+M">Mareike Thies</a>, <a href="/search/eess?searchtype=author&query=Maier%2C+A">Andreas Maier</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.11586v1-abstract-short" style="display: inline;"> The differentiable shift-variant filtered backprojection (FBP) model enables the reconstruction of cone-beam computed tomography (CBCT) data for any non-circular trajectories. This method employs deep learning technique to estimate the redundancy weights required for reconstruction, given knowledge of the specific trajectory at optimization time. However, computing the redundancy weight for each p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.11586v1-abstract-full').style.display = 'inline'; document.getElementById('2501.11586v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.11586v1-abstract-full" style="display: none;"> The differentiable shift-variant filtered backprojection (FBP) model enables the reconstruction of cone-beam computed tomography (CBCT) data for any non-circular trajectories. This method employs deep learning technique to estimate the redundancy weights required for reconstruction, given knowledge of the specific trajectory at optimization time. However, computing the redundancy weight for each projection remains computationally intensive. This paper presents a novel approach to compress and optimize the differentiable shift-variant FBP model based on Principal Component Analysis (PCA). We apply PCA to the redundancy weights learned from sinusoidal trajectory projection data, revealing significant parameter redundancy in the original model. By integrating PCA directly into the differentiable shift-variant FBP reconstruction pipeline, we develop a method that decomposes the redundancy weight layer parameters into a trainable eigenvector matrix, compressed weights, and a mean vector. This innovative technique achieves a remarkable 97.25% reduction in trainable parameters without compromising reconstruction accuracy. As a result, our algorithm significantly decreases the complexity of the differentiable shift-variant FBP model and greatly improves training speed. These improvements make the model substantially more practical for real-world applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.11586v1-abstract-full').style.display = 'none'; document.getElementById('2501.11586v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.11276">arXiv:2501.11276</a> <span> [<a href="https://arxiv.org/pdf/2501.11276">pdf</a>, <a href="https://arxiv.org/format/2501.11276">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> ITCFN: Incomplete Triple-Modal Co-Attention Fusion Network for Mild Cognitive Impairment Conversion Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hu%2C+X">Xiangyang Hu</a>, <a href="/search/eess?searchtype=author&query=Shen%2C+X">Xiangyu Shen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifei Sun</a>, <a href="/search/eess?searchtype=author&query=Shan%2C+X">Xuhao Shan</a>, <a href="/search/eess?searchtype=author&query=Min%2C+W">Wenwen Min</a>, <a href="/search/eess?searchtype=author&query=Su%2C+L">Liyilei Su</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+X">Xiaomao Fan</a>, <a href="/search/eess?searchtype=author&query=Elazab%2C+A">Ahmed Elazab</a>, <a href="/search/eess?searchtype=author&query=Ge%2C+R">Ruiquan Ge</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Changmiao Wang</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+X">Xiaopeng Fan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.11276v1-abstract-short" style="display: inline;"> Alzheimer's disease (AD) is a common neurodegenerative disease among the elderly. Early prediction and timely intervention of its prodromal stage, mild cognitive impairment (MCI), can decrease the risk of advancing to AD. Combining information from various modalities can significantly improve predictive accuracy. However, challenges such as missing data and heterogeneity across modalities complica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.11276v1-abstract-full').style.display = 'inline'; document.getElementById('2501.11276v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.11276v1-abstract-full" style="display: none;"> Alzheimer's disease (AD) is a common neurodegenerative disease among the elderly. Early prediction and timely intervention of its prodromal stage, mild cognitive impairment (MCI), can decrease the risk of advancing to AD. Combining information from various modalities can significantly improve predictive accuracy. However, challenges such as missing data and heterogeneity across modalities complicate multimodal learning methods as adding more modalities can worsen these issues. Current multimodal fusion techniques often fail to adapt to the complexity of medical data, hindering the ability to identify relationships between modalities. To address these challenges, we propose an innovative multimodal approach for predicting MCI conversion, focusing specifically on the issues of missing positron emission tomography (PET) data and integrating diverse medical information. The proposed incomplete triple-modal MCI conversion prediction network is tailored for this purpose. Through the missing modal generation module, we synthesize the missing PET data from the magnetic resonance imaging and extract features using specifically designed encoders. We also develop a channel aggregation module and a triple-modal co-attention fusion module to reduce feature redundancy and achieve effective multimodal data fusion. Furthermore, we design a loss function to handle missing modality issues and align cross-modal features. These components collectively harness multimodal data to boost network performance. Experimental results on the ADNI1 and ADNI2 datasets show that our method significantly surpasses existing unimodal and other multimodal models. Our code is available at https://github.com/justinhxy/ITFC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.11276v1-abstract-full').style.display = 'none'; document.getElementById('2501.11276v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 1 figure, accepted by IEEE ISBI 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.10753">arXiv:2501.10753</a> <span> [<a href="https://arxiv.org/pdf/2501.10753">pdf</a>, <a href="https://arxiv.org/ps/2501.10753">ps</a>, <a href="https://arxiv.org/format/2501.10753">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Pinching Antennas: Principles, Applications and Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yang%2C+Z">Zheng Yang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+N">Ning Wang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yanshi Sun</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+Z">Zhiguo Ding</a>, <a href="/search/eess?searchtype=author&query=Schober%2C+R">Robert Schober</a>, <a href="/search/eess?searchtype=author&query=Karagiannidis%2C+G+K">George K. Karagiannidis</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+V+W+S">Vincent W. S. Wong</a>, <a href="/search/eess?searchtype=author&query=Dobre%2C+O+A">Octavia A. Dobre</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.10753v1-abstract-short" style="display: inline;"> Flexible-antenna systems, such as fluid antennas and movable antennas, have been recognized as key enabling technologies for sixth-generation (6G) wireless networks, as they can intelligently reconfigure the effective channel gains of the users and hence significantly improve their data transmission capabilities. However, existing flexible-antenna systems have been designed to combat small-scale f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.10753v1-abstract-full').style.display = 'inline'; document.getElementById('2501.10753v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.10753v1-abstract-full" style="display: none;"> Flexible-antenna systems, such as fluid antennas and movable antennas, have been recognized as key enabling technologies for sixth-generation (6G) wireless networks, as they can intelligently reconfigure the effective channel gains of the users and hence significantly improve their data transmission capabilities. However, existing flexible-antenna systems have been designed to combat small-scale fading in non-line-of-sight (NLoS) conditions. As a result, they lack the ability to establish line-of-sight links, which are typically 100 times stronger than NLoS links. In addition, existing flexible-antenna systems have limited flexibility, where adding/removing an antenna is not straightforward. This article introduces an innovative flexible-antenna system called pinching antennas, which are realized by applying small dielectric particles to waveguides. We first describe the basics of pinching-antenna systems and their ability to provide strong LoS links by deploying pinching antennas close to the users as well as their capability to scale up/down the antenna system. We then focus on communication scenarios with different numbers of waveguides and pinching antennas, where innovative approaches to implement multiple-input multiple-output and non-orthogonal multiple access are discussed. In addition, promising 6G-related applications of pinching antennas, including integrated sensing and communication and next-generation multiple access, are presented. Finally, important directions for future research, such as waveguide deployment and channel estimation, are highlighted. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.10753v1-abstract-full').style.display = 'none'; document.getElementById('2501.10753v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.10404">arXiv:2501.10404</a> <span> [<a href="https://arxiv.org/pdf/2501.10404">pdf</a>, <a href="https://arxiv.org/format/2501.10404">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Dong%2C+H">Hanyang Dong</a>, <a href="/search/eess?searchtype=author&query=Sheng%2C+S">Shurong Sheng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xiongfei Wang</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+J">Jiahong Gao</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yi Sun</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+W">Wanli Yang</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+K">Kuntao Xiao</a>, <a href="/search/eess?searchtype=author&query=Teng%2C+P">Pengfei Teng</a>, <a href="/search/eess?searchtype=author&query=Luan%2C+G">Guoming Luan</a>, <a href="/search/eess?searchtype=author&query=Lv%2C+Z">Zhao Lv</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.10404v1-abstract-short" style="display: inline;"> A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal's intensity reflecting magnetic field changes over time at the sensor location. Automating epileptic MEG spike detection significantly reduces manual assessment time and effort, yielding substantial clinical benefits. Existing research addresses MEG spike de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.10404v1-abstract-full').style.display = 'inline'; document.getElementById('2501.10404v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.10404v1-abstract-full" style="display: none;"> A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal's intensity reflecting magnetic field changes over time at the sensor location. Automating epileptic MEG spike detection significantly reduces manual assessment time and effort, yielding substantial clinical benefits. Existing research addresses MEG spike detection by encoding neural network inputs with signals from all channel within a time segment, followed by classification. However, these methods overlook simultaneous spiking occurred from nearby sensors. We introduce a simple yet effective paradigm that first clusters MEG channels based on their sensor's spatial position. Next, a novel convolutional input module is designed to integrate the spatial clustering and temporal changes of the signals. This module is fed into a custom MEEG-ResNet3D developed by the authors, which learns to extract relevant features and classify the input as a spike clip or not. Our method achieves an F1 score of 94.73% on a large real-world MEG dataset Sanbo-CMR collected from two centers, outperforming state-of-the-art approaches by 1.85%. Moreover, it demonstrates efficacy and stability in the Electroencephalographic (EEG) seizure detection task, yielding an improved weighted F1 score of 1.4% compared to current state-of-the-art techniques evaluated on TUSZ, whch is the largest EEG seizure dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.10404v1-abstract-full').style.display = 'none'; document.getElementById('2501.10404v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 6 figures, accepted by BIBM2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.04490">arXiv:2501.04490</a> <span> [<a href="https://arxiv.org/pdf/2501.04490">pdf</a>, <a href="https://arxiv.org/ps/2501.04490">ps</a>, <a href="https://arxiv.org/format/2501.04490">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Rotatable and Movable Antenna-Enabled Near-Field Integrated Sensing and Communication </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yunan Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.04490v2-abstract-short" style="display: inline;"> Integrated sensing and communication (ISAC) is regarded as a promising technology for next-generation communication networks. As the demand for communication performance significantly increases, extremely large-scale antenna arrays and tremendously high-frequency bands get widely applied in communication systems, leading to the expansion of the near-field region. On a parallel track, movable anten… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04490v2-abstract-full').style.display = 'inline'; document.getElementById('2501.04490v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.04490v2-abstract-full" style="display: none;"> Integrated sensing and communication (ISAC) is regarded as a promising technology for next-generation communication networks. As the demand for communication performance significantly increases, extremely large-scale antenna arrays and tremendously high-frequency bands get widely applied in communication systems, leading to the expansion of the near-field region. On a parallel track, movable antennas (MAs) and six-dimensional MAs (6DMAs) are proposed as emerging technologies to improve the performance of communication and sensing. Based on such a background, this paper investigates the performance of ISAC systems in the near-field region, focusing on a novel system architecture that employs rotatable MAs (RMAs). Additionally, a spherical wave near-field channel model with respect to RMAs' rotations and positions is derived by considering the effective aperture loss. Two designs are explored: a sensing-centric design that minimizes the Cram茅r-Rao bound (CRB) with signal-to-interference-plus-noise ratio (SINR) constraints, and a communication-centric design that maximizes the sum-rate with a CRB constraint. To solve the formulated optimization problems, the paper proposes two alternating optimization (AO) based algorithms composed of the semidefinite relaxation (SDR) method and the particle swarm optimization (PSO) method. Numerical results demonstrate the convergence and effectiveness of the proposed algorithms and the superiority of the proposed setups for both sensing and communication performance compared to traditional fixed antenna systems, highlighting the potential of RMAs to enhance ISAC systems in near-field scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04490v2-abstract-full').style.display = 'none'; document.getElementById('2501.04490v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 6 figures, due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract appearing here is slightly shorter than that in the PDF file</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.03605">arXiv:2501.03605</a> <span> [<a href="https://arxiv.org/pdf/2501.03605">pdf</a>, <a href="https://arxiv.org/format/2501.03605">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian Splatting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yang%2C+Y">Yifeng Yang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+H">Hengyu Liu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenxin Li</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yining Sun</a>, <a href="/search/eess?searchtype=author&query=Li%2C+W">Wuyang Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yifan Liu</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+Y">Yiyang Lin</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+Y">Yixuan Yuan</a>, <a href="/search/eess?searchtype=author&query=Ye%2C+N">Nanyang Ye</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.03605v1-abstract-short" style="display: inline;"> With the rapid development of 3D reconstruction technology, the widespread distribution of 3D data has become a future trend. While traditional visual data (such as images and videos) and NeRF-based formats already have mature techniques for copyright protection, steganographic techniques for the emerging 3D Gaussian Splatting (3D-GS) format have yet to be fully explored. To address this, we propo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.03605v1-abstract-full').style.display = 'inline'; document.getElementById('2501.03605v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.03605v1-abstract-full" style="display: none;"> With the rapid development of 3D reconstruction technology, the widespread distribution of 3D data has become a future trend. While traditional visual data (such as images and videos) and NeRF-based formats already have mature techniques for copyright protection, steganographic techniques for the emerging 3D Gaussian Splatting (3D-GS) format have yet to be fully explored. To address this, we propose ConcealGS, an innovative method for embedding implicit information into 3D-GS. By introducing the knowledge distillation and gradient optimization strategy based on 3D-GS, ConcealGS overcomes the limitations of NeRF-based models and enhances the robustness of implicit information and the quality of 3D reconstruction. We evaluate ConcealGS in various potential application scenarios, and experimental results have demonstrated that ConcealGS not only successfully recovers implicit information but also has almost no impact on rendering quality, providing a new approach for embedding invisible and recoverable information into 3D models in the future. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.03605v1-abstract-full').style.display = 'none'; document.getElementById('2501.03605v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.02572">arXiv:2501.02572</a> <span> [<a href="https://arxiv.org/pdf/2501.02572">pdf</a>, <a href="https://arxiv.org/format/2501.02572">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Energy Optimization of Multi-task DNN Inference in MEC-assisted XR Devices: A Lyapunov-Guided Reinforcement Learning Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yanzan Sun</a>, <a href="/search/eess?searchtype=author&query=Qiu%2C+J">Jiacheng Qiu</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+G">Guangjin Pan</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+S">Shugong Xu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shunqing Zhang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xiaoyun Wang</a>, <a href="/search/eess?searchtype=author&query=Han%2C+S">Shuangfeng Han</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.02572v1-abstract-short" style="display: inline;"> Extended reality (XR), blending virtual and real worlds, is a key application of future networks. While AI advancements enhance XR capabilities, they also impose significant computational and energy challenges on lightweight XR devices. In this paper, we developed a distributed queue model for multi-task DNN inference, addressing issues of resource competition and queue coupling. In response to th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02572v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02572v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02572v1-abstract-full" style="display: none;"> Extended reality (XR), blending virtual and real worlds, is a key application of future networks. While AI advancements enhance XR capabilities, they also impose significant computational and energy challenges on lightweight XR devices. In this paper, we developed a distributed queue model for multi-task DNN inference, addressing issues of resource competition and queue coupling. In response to the challenges posed by the high energy consumption and limited resources of XR devices, we designed a dual time-scale joint optimization strategy for model partitioning and resource allocation, formulated as a bi-level optimization problem. This strategy aims to minimize the total energy consumption of XR devices while ensuring queue stability and adhering to computational and communication resource constraints. To tackle this problem, we devised a Lyapunov-guided Proximal Policy Optimization algorithm, named LyaPPO. Numerical results demonstrate that the LyaPPO algorithm outperforms the baselines, achieving energy conservation of 24.79% to 46.14% under varying resource capacities. Specifically, the proposed algorithm reduces the energy consumption of XR devices by 24.29% to 56.62% compared to baseline algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02572v1-abstract-full').style.display = 'none'; document.getElementById('2501.02572v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 7 figures. This work has been submitted to the IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.02458">arXiv:2501.02458</a> <span> [<a href="https://arxiv.org/pdf/2501.02458">pdf</a>, <a href="https://arxiv.org/format/2501.02458">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Neural Reflectance Fields for Radio-Frequency Ray Tracing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jia%2C+H">Haifeng Jia</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xinyi Chen</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+Y">Yichen Wei</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifei Sun</a>, <a href="/search/eess?searchtype=author&query=Pi%2C+Y">Yibo Pi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.02458v1-abstract-short" style="display: inline;"> Ray tracing is widely employed to model the propagation of radio-frequency (RF) signal in complex environment. The modelling performance greatly depends on how accurately the target scene can be depicted, including the scene geometry and surface material properties. The advances in computer vision and LiDAR make scene geometry estimation increasingly accurate, but there still lacks scalable and ef… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02458v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02458v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02458v1-abstract-full" style="display: none;"> Ray tracing is widely employed to model the propagation of radio-frequency (RF) signal in complex environment. The modelling performance greatly depends on how accurately the target scene can be depicted, including the scene geometry and surface material properties. The advances in computer vision and LiDAR make scene geometry estimation increasingly accurate, but there still lacks scalable and efficient approaches to estimate the material reflectivity in real-world environment. In this work, we tackle this problem by learning the material reflectivity efficiently from the path loss of the RF signal from the transmitters to receivers. Specifically, we want the learned material reflection coefficients to minimize the gap between the predicted and measured powers of the receivers. We achieve this by translating the neural reflectance field from optics to RF domain by modelling both the amplitude and phase of RF signals to account for the multipath effects. We further propose a differentiable RF ray tracing framework that optimizes the neural reflectance field to match the signal strength measurements. We simulate a complex real-world environment for experiments and our simulation results show that the neural reflectance field can successfully learn the reflection coefficients for all incident angles. As a result, our approach achieves better accuracy in predicting the powers of receivers with significantly less training data compared to existing approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02458v1-abstract-full').style.display = 'none'; document.getElementById('2501.02458v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE Global Communications Conference 2024 (GLOBECOM'24)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.02099">arXiv:2501.02099</a> <span> [<a href="https://arxiv.org/pdf/2501.02099">pdf</a>, <a href="https://arxiv.org/format/2501.02099">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Timely Remote Estimation with Memory at the Receiver </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chakraborty%2C+S">Sirin Chakraborty</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yin Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.02099v1-abstract-short" style="display: inline;"> In this study, we consider a remote estimation system that estimates a time-varying target based on sensor data transmitted over wireless channel. Due to transmission errors, some data packets fail to reach the receiver. To mitigate this, the receiver uses a buffer to store recently received data packets, which allows for more accurate estimation from the incomplete received data. Our research foc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02099v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02099v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02099v1-abstract-full" style="display: none;"> In this study, we consider a remote estimation system that estimates a time-varying target based on sensor data transmitted over wireless channel. Due to transmission errors, some data packets fail to reach the receiver. To mitigate this, the receiver uses a buffer to store recently received data packets, which allows for more accurate estimation from the incomplete received data. Our research focuses on optimizing the transmission scheduling policy to minimize the estimation error, which is quantified as a function of the age of information vector associated with the buffered packets. Our results show that maintaining a buffer at the receiver results in better estimation performance for non-Markovian sources. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02099v1-abstract-full').style.display = 'none'; document.getElementById('2501.02099v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 3 figures, to be published in the Proceedings of the 2024 Asilomar Conference on Signals, Systems, and Computers, October 27-30, 2023, Pacific Grove, California, USA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.20788">arXiv:2412.20788</a> <span> [<a href="https://arxiv.org/pdf/2412.20788">pdf</a>, <a href="https://arxiv.org/format/2412.20788">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> An Experimental Study of Passive UAV Tracking with Digital Arrays and Cellular Downlink Signals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifei Sun</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+C">Chao Yu</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+Y">Yan Luo</a>, <a href="/search/eess?searchtype=author&query=Han%2C+T+X">Tony Xiao Han</a>, <a href="/search/eess?searchtype=author&query=Tan%2C+H">Haisheng Tan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+R">Rui Wang</a>, <a href="/search/eess?searchtype=author&query=Lau%2C+F+C+M">Francis C. M. Lau</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.20788v1-abstract-short" style="display: inline;"> Given the prospects of the low-altitude economy (LAE) and the popularity of unmanned aerial vehicles (UAVs), there are increasing demands on monitoring flying objects at low altitude in wide urban areas. In this work, the widely deployed long-term evolution (LTE) base station (BS) is exploited to illuminate UAVs in bistatic trajectory tracking. Specifically, a passive sensing receiver with two dig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.20788v1-abstract-full').style.display = 'inline'; document.getElementById('2412.20788v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.20788v1-abstract-full" style="display: none;"> Given the prospects of the low-altitude economy (LAE) and the popularity of unmanned aerial vehicles (UAVs), there are increasing demands on monitoring flying objects at low altitude in wide urban areas. In this work, the widely deployed long-term evolution (LTE) base station (BS) is exploited to illuminate UAVs in bistatic trajectory tracking. Specifically, a passive sensing receiver with two digital antenna arrays is proposed and developed to capture both the line-of-sight (LoS) signal and the scattered signal off a target UAV. From their cross ambiguity function, the bistatic range, Doppler shift and angle-of-arrival (AoA) of the target UAV can be detected in a sequence of time slots. In order to address missed detections and false alarms of passive sensing, a multi-target tracking framework is adopted to track the trajectory of the target UAV. It is demonstrated by experiments that the proposed UAV tracking system can achieve a meter-level accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.20788v1-abstract-full').style.display = 'none'; document.getElementById('2412.20788v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 10 figures, submitted to IEEE Journal for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.18727">arXiv:2412.18727</a> <span> [<a href="https://arxiv.org/pdf/2412.18727">pdf</a>, <a href="https://arxiv.org/format/2412.18727">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> SAFLITE: Fuzzing Autonomous Systems via Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhu%2C+T">Taohong Zhu</a>, <a href="/search/eess?searchtype=author&query=Skapars%2C+A">Adrians Skapars</a>, <a href="/search/eess?searchtype=author&query=Mackenzie%2C+F">Fardeen Mackenzie</a>, <a href="/search/eess?searchtype=author&query=Kehoe%2C+D">Declan Kehoe</a>, <a href="/search/eess?searchtype=author&query=Newton%2C+W">William Newton</a>, <a href="/search/eess?searchtype=author&query=Embury%2C+S">Suzanne Embury</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Youcheng Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.18727v1-abstract-short" style="display: inline;"> Fuzz testing effectively uncovers software vulnerabilities; however, it faces challenges with Autonomous Systems (AS) due to their vast search spaces and complex state spaces, which reflect the unpredictability and complexity of real-world environments. This paper presents a universal framework aimed at improving the efficiency of fuzz testing for AS. At its core is SaFliTe, a predictive component… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18727v1-abstract-full').style.display = 'inline'; document.getElementById('2412.18727v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.18727v1-abstract-full" style="display: none;"> Fuzz testing effectively uncovers software vulnerabilities; however, it faces challenges with Autonomous Systems (AS) due to their vast search spaces and complex state spaces, which reflect the unpredictability and complexity of real-world environments. This paper presents a universal framework aimed at improving the efficiency of fuzz testing for AS. At its core is SaFliTe, a predictive component that evaluates whether a test case meets predefined safety criteria. By leveraging the large language model (LLM) with information about the test objective and the AS state, SaFliTe assesses the relevance of each test case. We evaluated SaFliTe by instantiating it with various LLMs, including GPT-3.5, Mistral-7B, and Llama2-7B, and integrating it into four fuzz testing tools: PGFuzz, DeepHyperion-UAV, CAMBA, and TUMB. These tools are designed specifically for testing autonomous drone control systems, such as ArduPilot, PX4, and PX4-Avoidance. The experimental results demonstrate that, compared to PGFuzz, SaFliTe increased the likelihood of selecting operations that triggered bug occurrences in each fuzzing iteration by an average of 93.1\%. Additionally, after integrating SaFliTe, the ability of DeepHyperion-UAV, CAMBA, and TUMB to generate test cases that caused system violations increased by 234.5\%, 33.3\%, and 17.8\%, respectively. The benchmark for this evaluation was sourced from a UAV Testing Competition. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18727v1-abstract-full').style.display = 'none'; document.getElementById('2412.18727v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.15670">arXiv:2412.15670</a> <span> [<a href="https://arxiv.org/pdf/2412.15670">pdf</a>, <a href="https://arxiv.org/format/2412.15670">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> BS-LDM: Effective Bone Suppression in High-Resolution Chest X-Ray Images with Conditional Latent Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifei Sun</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhanghao Chen</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+H">Hao Zheng</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+W">Wenming Deng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+J">Jin Liu</a>, <a href="/search/eess?searchtype=author&query=Min%2C+W">Wenwen Min</a>, <a href="/search/eess?searchtype=author&query=Elazab%2C+A">Ahmed Elazab</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+X">Xiang Wan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Changmiao Wang</a>, <a href="/search/eess?searchtype=author&query=Ge%2C+R">Ruiquan Ge</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.15670v3-abstract-short" style="display: inline;"> Lung diseases represent a significant global health challenge, with Chest X-Ray (CXR) being a key diagnostic tool due to their accessibility and affordability. Nonetheless, the detection of pulmonary lesions is often hindered by overlapping bone structures in CXR images, leading to potential misdiagnoses. To address this issue, we developed an end-to-end framework called BS-LDM, designed to effect… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15670v3-abstract-full').style.display = 'inline'; document.getElementById('2412.15670v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.15670v3-abstract-full" style="display: none;"> Lung diseases represent a significant global health challenge, with Chest X-Ray (CXR) being a key diagnostic tool due to their accessibility and affordability. Nonetheless, the detection of pulmonary lesions is often hindered by overlapping bone structures in CXR images, leading to potential misdiagnoses. To address this issue, we developed an end-to-end framework called BS-LDM, designed to effectively suppress bone in high-resolution CXR images. This framework is based on conditional latent diffusion models and incorporates a multi-level hybrid loss-constrained vector-quantized generative adversarial network which is crafted for perceptual compression, ensuring the preservation of details. To further enhance the framework's performance, we introduce offset noise and a temporal adaptive thresholding strategy. These additions help minimize discrepancies in generating low-frequency information, thereby improving the clarity of the generated soft tissue images. Additionally, we have compiled a high-quality bone suppression dataset named SZCH-X-Rays. This dataset includes 818 pairs of high-resolution CXR and dual-energy subtraction soft tissue images collected from a partner hospital. Moreover, we processed 241 data pairs from the JSRT dataset into negative images, which are more commonly used in clinical practice. Our comprehensive experimental and clinical evaluations reveal that BS-LDM excels in bone suppression, underscoring its significant clinical value. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15670v3-abstract-full').style.display = 'none'; document.getElementById('2412.15670v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 7 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.11907">arXiv:2412.11907</a> <span> [<a href="https://arxiv.org/pdf/2412.11907">pdf</a>, <a href="https://arxiv.org/format/2412.11907">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> AudioCIL: A Python Toolbox for Audio Class-Incremental Learning with Multiple Scenes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+Q">Qisheng Xu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yulin Sun</a>, <a href="/search/eess?searchtype=author&query=Su%2C+Y">Yi Su</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+Q">Qian Zhu</a>, <a href="/search/eess?searchtype=author&query=Tan%2C+X">Xiaoyi Tan</a>, <a href="/search/eess?searchtype=author&query=Wen%2C+H">Hongyu Wen</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Z">Zijian Gao</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+K">Kele Xu</a>, <a href="/search/eess?searchtype=author&query=Dou%2C+Y">Yong Dou</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+D">Dawei Feng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.11907v2-abstract-short" style="display: inline;"> Deep learning, with its robust aotomatic feature extraction capabilities, has demonstrated significant success in audio signal processing. Typically, these methods rely on static, pre-collected large-scale datasets for training, performing well on a fixed number of classes. However, the real world is characterized by constant change, with new audio classes emerging from streaming or temporary avai… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11907v2-abstract-full').style.display = 'inline'; document.getElementById('2412.11907v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.11907v2-abstract-full" style="display: none;"> Deep learning, with its robust aotomatic feature extraction capabilities, has demonstrated significant success in audio signal processing. Typically, these methods rely on static, pre-collected large-scale datasets for training, performing well on a fixed number of classes. However, the real world is characterized by constant change, with new audio classes emerging from streaming or temporary availability due to privacy. This dynamic nature of audio environments necessitates models that can incrementally learn new knowledge for new classes without discarding existing information. Introducing incremental learning to the field of audio signal processing, i.e., Audio Class-Incremental Learning (AuCIL), is a meaningful endeavor. We propose such a toolbox named AudioCIL to align audio signal processing algorithms with real-world scenarios and strengthen research in audio class-incremental learning. Code is available at https://github.com/colaudiolab/AudioCIL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11907v2-abstract-full').style.display = 'none'; document.getElementById('2412.11907v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.11399">arXiv:2412.11399</a> <span> [<a href="https://arxiv.org/pdf/2412.11399">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Quantization of Climate Change Impacts on Renewable Energy Generation Capacity: A Super-Resolution Recurrent Diffusion Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Dong%2C+X">Xiaochong Dong</a>, <a href="/search/eess?searchtype=author&query=Dan%2C+J">Jun Dan</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yingyun Sun</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xuemin Zhang</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+S">Shengwei Mei</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.11399v1-abstract-short" style="display: inline;"> Driven by global climate change and the ongoing energy transition, the coupling between power supply capabilities and meteorological factors has become increasingly significant. Over the long term, accurately quantifying the power generation capacity of renewable energy under the influence of climate change is essential for the development of sustainable power systems. However, due to interdiscipl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11399v1-abstract-full').style.display = 'inline'; document.getElementById('2412.11399v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.11399v1-abstract-full" style="display: none;"> Driven by global climate change and the ongoing energy transition, the coupling between power supply capabilities and meteorological factors has become increasingly significant. Over the long term, accurately quantifying the power generation capacity of renewable energy under the influence of climate change is essential for the development of sustainable power systems. However, due to interdisciplinary differences in data requirements, climate data often lacks the necessary hourly resolution to capture the short-term variability and uncertainties of renewable energy resources. To address this limitation, a super-resolution recurrent diffusion model (SRDM) has been developed to enhance the temporal resolution of climate data and model the short-term uncertainty. The SRDM incorporates a pre-trained decoder and a denoising network, that generates long-term, high-resolution climate data through a recurrent coupling mechanism. The high-resolution climate data is then converted into power value using the mechanism model, enabling the simulation of wind and photovoltaic (PV) power generation capacity on future long-term scales. Case studies were conducted in the Ejina region of Inner Mongolia, China, using fifth-generation reanalysis (ERA5) and coupled model intercomparison project (CMIP6) data under two climate pathways: SSP126 and SSP585. The results demonstrate that the SRDM outperforms existing generative models in generating super-resolution climate data. For the Ejina region, under a high-emission pathway, the annual utilization hours of wind power are projected to decrease by 2.82 hours/year, while those for PV power are projected to decrease by 0.26 hours/year. Furthermore, the research highlights the estimation biases introduced when low-resolution climate data is used for power conversion. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.11399v1-abstract-full').style.display = 'none'; document.getElementById('2412.11399v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.08856">arXiv:2412.08856</a> <span> [<a href="https://arxiv.org/pdf/2412.08856">pdf</a>, <a href="https://arxiv.org/format/2412.08856">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yi Li</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yang Sun</a>, <a href="/search/eess?searchtype=author&query=Angelov%2C+P">Plamen Angelov</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.08856v1-abstract-short" style="display: inline;"> In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion process, noise clips from real-world noise interferences are added gradually to the clean speech spectra and a noise-aware reverse process is proposed to learn how to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08856v1-abstract-full').style.display = 'inline'; document.getElementById('2412.08856v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.08856v1-abstract-full" style="display: none;"> In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion process, noise clips from real-world noise interferences are added gradually to the clean speech spectra and a noise-aware reverse process is proposed to learn how to generate both clean speech spectra and noise spectra. Furthermore, to fully leverage the intrinsic relationship between magnitude and phase, we introduce a complex-cycle-consistent (CCC) mechanism that uses the estimated magnitude to map the phase, and vice versa. We implement this algorithm within a phase-aware speech enhancement diffusion model (SEDM). We conduct extensive experiments on public datasets to demonstrate the effectiveness of our method, highlighting the significant benefits of exploiting the intrinsic relationship between phase and magnitude information to enhance speech. The comparison to conventional diffusion models demonstrates the superiority of SEDM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.08856v1-abstract-full').style.display = 'none'; document.getElementById('2412.08856v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">AAAI 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.17745">arXiv:2411.17745</a> <span> [<a href="https://arxiv.org/pdf/2411.17745">pdf</a>, <a href="https://arxiv.org/format/2411.17745">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> A Parameter Adaptive Trajectory Tracking and Motion Control Framework for Autonomous Vehicle </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Song%2C+J">Jiarui Song</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yingbo Sun</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+Q">Qing Dong</a>, <a href="/search/eess?searchtype=author&query=Ji%2C+X">Xuewu Ji</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.17745v1-abstract-short" style="display: inline;"> This paper studies the trajectory tracking and motion control problems for autonomous vehicles (AVs). A parameter adaptive control framework for AVs is proposed to enhance tracking accuracy and yaw stability. While establishing linear quadratic regulator (LQR) and three robust controllers, the control framework addresses trajectory tracking and motion control in a modular fashion, without introduc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17745v1-abstract-full').style.display = 'inline'; document.getElementById('2411.17745v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.17745v1-abstract-full" style="display: none;"> This paper studies the trajectory tracking and motion control problems for autonomous vehicles (AVs). A parameter adaptive control framework for AVs is proposed to enhance tracking accuracy and yaw stability. While establishing linear quadratic regulator (LQR) and three robust controllers, the control framework addresses trajectory tracking and motion control in a modular fashion, without introducing complexity into each controller. The robust performance has been guaranteed in three robust controllers by considering the parameter uncertainties, mismatch of unmodeled subsystem as well as external disturbance, comprehensively. Also, the dynamic characteristics of uncertain parameters are identified by Recursive Least Squares (RLS) algorithm, while the boundaries of three robust factors are determined through combining Gaussian Process Regression (GPR) and Bayesian optimization machine learning methods, reducing the conservatism of the controller. Sufficient conditions for closed-loop stability under the diverse robust factors are provided by the Lyapunov method analytically. The simulation results on MATLAB/Simulink and Carsim joint platform demonstrate that the proposed methodology considerably improves tracking accuracy, driving stability, and robust performance, guaranteeing the feasibility and capability of driving in extreme scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.17745v1-abstract-full').style.display = 'none'; document.getElementById('2411.17745v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.16629">arXiv:2411.16629</a> <span> [<a href="https://arxiv.org/pdf/2411.16629">pdf</a>, <a href="https://arxiv.org/format/2411.16629">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> LegoPET: Hierarchical Feature Guided Conditional Diffusion for PET Image Reconstruction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yiran Sun</a>, <a href="/search/eess?searchtype=author&query=Mawlawi%2C+O">Osama Mawlawi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.16629v1-abstract-short" style="display: inline;"> Positron emission tomography (PET) is widely utilized for cancer detection due to its ability to visualize functional and biological processes in vivo. PET images are usually reconstructed from histogrammed raw data (sinograms) using traditional iterative techniques (e.g., OSEM, MLEM). Recently, deep learning (DL) methods have shown promise by directly mapping raw sinogram data to PET images. Howe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.16629v1-abstract-full').style.display = 'inline'; document.getElementById('2411.16629v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.16629v1-abstract-full" style="display: none;"> Positron emission tomography (PET) is widely utilized for cancer detection due to its ability to visualize functional and biological processes in vivo. PET images are usually reconstructed from histogrammed raw data (sinograms) using traditional iterative techniques (e.g., OSEM, MLEM). Recently, deep learning (DL) methods have shown promise by directly mapping raw sinogram data to PET images. However, DL approaches that are regression-based or GAN-based often produce overly smoothed images or introduce various artifacts respectively. Image-conditioned diffusion probabilistic models (cDPMs) are another class of likelihood-based DL techniques capable of generating highly realistic and controllable images. While cDPMs have notable strengths, they still face challenges such as maintain correspondence and consistency between input and output images when they are from different domains (e.g., sinogram vs. image domain) as well as slow convergence rates. To address these limitations, we introduce LegoPET, a hierarchical feature guided conditional diffusion model for high-perceptual quality PET image reconstruction from sinograms. We conducted several experiments demonstrating that LegoPET not only improves the performance of cDPMs but also surpasses recent DL-based PET image reconstruction techniques in terms of visual quality and pixel-level PSNR/SSIM metrics. Our code is available at https://github.com/yransun/LegoPET. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.16629v1-abstract-full').style.display = 'none'; document.getElementById('2411.16629v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 3 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11576">arXiv:2411.11576</a> <span> [<a href="https://arxiv.org/pdf/2411.11576">pdf</a>, <a href="https://arxiv.org/format/2411.11576">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Hybrid Data-Driven SSM for Interpretable and Label-Free mmWave Channel Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yiyong Sun</a>, <a href="/search/eess?searchtype=author&query=He%2C+J">Jiajun He</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+Z">Zhidi Lin</a>, <a href="/search/eess?searchtype=author&query=Pu%2C+W">Wenqiang Pu</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+F">Feng Yin</a>, <a href="/search/eess?searchtype=author&query=So%2C+H+C">Hing Cheung So</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11576v1-abstract-short" style="display: inline;"> Accurate prediction of mmWave time-varying channels is essential for mitigating the issue of channel aging in complex scenarios owing to high user mobility. Existing channel prediction methods have limitations: classical model-based methods often struggle to track highly nonlinear channel dynamics due to limited expert knowledge, while emerging data-driven methods typically require substantial lab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11576v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11576v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11576v1-abstract-full" style="display: none;"> Accurate prediction of mmWave time-varying channels is essential for mitigating the issue of channel aging in complex scenarios owing to high user mobility. Existing channel prediction methods have limitations: classical model-based methods often struggle to track highly nonlinear channel dynamics due to limited expert knowledge, while emerging data-driven methods typically require substantial labeled data for effective training and often lack interpretability. To address these issues, this paper proposes a novel hybrid method that integrates a data-driven neural network into a conventional model-based workflow based on a state-space model (SSM), implicitly tracking complex channel dynamics from data without requiring precise expert knowledge. Additionally, a novel unsupervised learning strategy is developed to train the embedded neural network solely with unlabeled data. Theoretical analyses and ablation studies are conducted to interpret the enhanced benefits gained from the hybrid integration. Numerical simulations based on the 3GPP mmWave channel model corroborate the superior prediction accuracy of the proposed method, compared to state-of-the-art methods that are either purely model-based or data-driven. Furthermore, extensive experiments validate its robustness against various challenging factors, including among others severe channel variations and high noise levels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11576v1-abstract-full').style.display = 'none'; document.getElementById('2411.11576v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.11030">arXiv:2411.11030</a> <span> [<a href="https://arxiv.org/pdf/2411.11030">pdf</a>, <a href="https://arxiv.org/format/2411.11030">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> IREE Oriented Active RIS-Assisted Green communication System with Outdated CSI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Cao%2C+K">Kai Cao</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+T">Tao Yu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jihong Li</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xiaojing Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yanzan Sun</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Q">Qingqing Wu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+W">Wen Chen</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shunqing Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.11030v1-abstract-short" style="display: inline;"> The rapid evolution of communication technologies has spurred a growing demand for energy-efficient network architectures and performance metrics. Active Reconfigurable Intelligent Surfaces (RIS) are emerging as a key component in green network architectures. Compared to passive RIS, active RIS are equipped with amplifiers on each reflecting element, allowing them to simultaneously reflect and amp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11030v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11030v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11030v1-abstract-full" style="display: none;"> The rapid evolution of communication technologies has spurred a growing demand for energy-efficient network architectures and performance metrics. Active Reconfigurable Intelligent Surfaces (RIS) are emerging as a key component in green network architectures. Compared to passive RIS, active RIS are equipped with amplifiers on each reflecting element, allowing them to simultaneously reflect and amplify signals, thereby overcoming the double multiplicative fading in the phase response, and improving both system coverage and performance. Additionally, the Integrated Relative Energy Efficiency (IREE) metric, as introduced in [1], addresses the dynamic variations in traffic and capacity over time and space, enabling more energy-efficient wireless systems. Building on these advancements, this paper investigates the problem of maximizing IREE in active RIS-assisted green communication systems. However, acquiring perfect Channel State Information (CSI) in practical systems poses significant challenges and costs. To address this, we derive the average achievable rate based on outdated CSI and formulated the corresponding IREE maximization problem, which is solved by jointly optimizing beamforming at both the base station and RIS. Given the non-convex nature of the problem, we propose an Alternating Optimization Successive Approximation (AOSO) algorithm. By applying quadratic transform and relaxation techniques, we simplify the original problem and alternately optimize the beamforming matrices at the base station and RIS. Furthermore, to handle the discrete constraints of the RIS reflection coefficients, we develop a successive approximation method. Experimental results validate our theoretical analysis of the algorithm's convergence , demonstrating the effectiveness of the proposed algorithm and highlighting the superiority of IREE in enhancing the performance of green communication networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11030v1-abstract-full').style.display = 'none'; document.getElementById('2411.11030v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10739">arXiv:2411.10739</a> <span> [<a href="https://arxiv.org/pdf/2411.10739">pdf</a>, <a href="https://arxiv.org/format/2411.10739">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> A Wearable Gait Monitoring System for 17 Gait Parameters Based on Computer Vision </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jiangang Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yung-Hong Sun</a>, <a href="/search/eess?searchtype=author&query=Pickett%2C+K">Kristen Pickett</a>, <a href="/search/eess?searchtype=author&query=King%2C+B">Barbara King</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Y+H">Yu Hen Hu</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+H">Hongrui Jiang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10739v1-abstract-short" style="display: inline;"> We developed a shoe-mounted gait monitoring system capable of tracking up to 17 gait parameters, including gait length, step time, stride velocity, and others. The system employs a stereo camera mounted on one shoe to track a marker placed on the opposite shoe, enabling the estimation of spatial gait parameters. Additionally, a Force Sensitive Resistor (FSR) affixed to the heel of the shoe, combin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10739v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10739v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10739v1-abstract-full" style="display: none;"> We developed a shoe-mounted gait monitoring system capable of tracking up to 17 gait parameters, including gait length, step time, stride velocity, and others. The system employs a stereo camera mounted on one shoe to track a marker placed on the opposite shoe, enabling the estimation of spatial gait parameters. Additionally, a Force Sensitive Resistor (FSR) affixed to the heel of the shoe, combined with a custom-designed algorithm, is utilized to measure temporal gait parameters. Through testing on multiple participants and comparison with the gait mat, the proposed gait monitoring system exhibited notable performance, with the accuracy of all measured gait parameters exceeding 93.61%. The system also demonstrated a low drift of 4.89% during long-distance walking. A gait identification task conducted on participants using a trained Transformer model achieved 95.7% accuracy on the dataset collected by the proposed system, demonstrating that our hardware has the potential to collect long-sequence gait data suitable for integration with current Large Language Models (LLMs). The system is cost-effective, user-friendly, and well-suited for real-life measurements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10739v1-abstract-full').style.display = 'none'; document.getElementById('2411.10739v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 14 figures. This paper was submitted for publication to the IEEE Transactions on Instrumentation and Measurement</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.06107">arXiv:2411.06107</a> <span> [<a href="https://arxiv.org/pdf/2411.06107">pdf</a>, <a href="https://arxiv.org/format/2411.06107">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> A capacity renting framework for shared energy storage considering peer-to-peer energy trading of prosumers with privacy protection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yingcong Sun</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+L">Laijun Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Yue Chen</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+M">Mingrui Tang</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+S">Shengwei Mei</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.06107v2-abstract-short" style="display: inline;"> Shared energy storage systems (ESS) present a promising solution to the temporal imbalance between energy generation from renewable distributed generators (DGs) and the power demands of prosumers. However, as DG penetration rates rise, spatial energy imbalances become increasingly significant, necessitating the integration of peer-to-peer (P2P) energy trading within the shared ESS framework. Two k… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06107v2-abstract-full').style.display = 'inline'; document.getElementById('2411.06107v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.06107v2-abstract-full" style="display: none;"> Shared energy storage systems (ESS) present a promising solution to the temporal imbalance between energy generation from renewable distributed generators (DGs) and the power demands of prosumers. However, as DG penetration rates rise, spatial energy imbalances become increasingly significant, necessitating the integration of peer-to-peer (P2P) energy trading within the shared ESS framework. Two key challenges emerge in this context: the absence of effective mechanisms and the greater difficulty for privacy protection due to increased data communication. This research proposes a capacity renting framework for shared ESS considering P2P energy trading of prosumers. In the proposed framework, prosumers can participate in P2P energy trading and rent capacities from shared ESS. A generalized Nash game is formulated to model the trading process and the competitive interactions among prosumers, and the variational equilibrium of the game is proved to be equivalent to the optimal solution of a quadratic programming (QP) problem. To address the privacy protection concern, the problem is solved using the alternating direction method of multipliers (ADMM) with the Paillier cryptosystem. Finally, numerical simulations demonstrate the impact of P2P energy trading on the shared ESS framework and validate the effectiveness of the proposed privacy-preserving algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.06107v2-abstract-full').style.display = 'none'; document.getElementById('2411.06107v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03127">arXiv:2411.03127</a> <span> [<a href="https://arxiv.org/pdf/2411.03127">pdf</a>, <a href="https://arxiv.org/format/2411.03127">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Receiver-Centric Generative Semantic Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+X">Xunze Liu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifei Sun</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zhaorui Wang</a>, <a href="/search/eess?searchtype=author&query=You%2C+L">Lizhao You</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+H">Haoyuan Pan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+F">Fangxin Wang</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+S">Shuguang Cui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03127v2-abstract-short" style="display: inline;"> This paper investigates semantic communications between a transmitter and a receiver, where original data, such as videos of interest to the receiver, is stored at the transmitter. Although significant process has been made in semantic communications, a fundamental design problem is that the semantic information is extracted based on certain criteria at the transmitter alone, without considering t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03127v2-abstract-full').style.display = 'inline'; document.getElementById('2411.03127v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03127v2-abstract-full" style="display: none;"> This paper investigates semantic communications between a transmitter and a receiver, where original data, such as videos of interest to the receiver, is stored at the transmitter. Although significant process has been made in semantic communications, a fundamental design problem is that the semantic information is extracted based on certain criteria at the transmitter alone, without considering the receiver's specific information needs. As a result, critical information of primary concern to the receiver may be lost. In such cases, the semantic transmission becomes meaningless to the receiver, as all received information is irrelevant to its interests. To solve this problem, this paper presents a receiver-centric generative semantic communication system, where each transmission is initialized by the receiver. Specifically, the receiver first sends its request for the desired semantic information to the transmitter at the start of each transmission. Then, the transmitter extracts the required semantic information accordingly. A key challenge is how the transmitter understands the receiver's requests for semantic information and extracts the required semantic information in a reasonable and robust manner. We address this challenge by designing a well-structured framework and leveraging off-the-shelf generative AI products, such as GPT-4, along with several specialized tools for detection and estimation. Evaluation results demonstrate the feasibility and effectiveness of the proposed new semantic communication system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03127v2-abstract-full').style.display = 'none'; document.getElementById('2411.03127v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Demo video has been made available at: https://goo.su/dUnAT</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01776">arXiv:2411.01776</a> <span> [<a href="https://arxiv.org/pdf/2411.01776">pdf</a>, <a href="https://arxiv.org/ps/2411.01776">ps</a>, <a href="https://arxiv.org/format/2411.01776">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> On Energy Efficiency of Hybrid NOMA </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yanshi Sun</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+Z">Zhiguo Ding</a>, <a href="/search/eess?searchtype=author&query=Hou%2C+Y">Yun Hou</a>, <a href="/search/eess?searchtype=author&query=Karagiannidis%2C+G+K">George K. Karagiannidis</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.01776v1-abstract-short" style="display: inline;"> This paper aims to prove the significant superiority of hybrid non-orthogonal multiple access (NOMA) over orthog onal multiple access (OMA) in terms of energy efficiency. In particular, a novel hybrid NOMA scheme is proposed in which a user can transmit signals not only by using its own time slot but also by using the time slots of other users. The data rate maximization problem is studied by opti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01776v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01776v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01776v1-abstract-full" style="display: none;"> This paper aims to prove the significant superiority of hybrid non-orthogonal multiple access (NOMA) over orthog onal multiple access (OMA) in terms of energy efficiency. In particular, a novel hybrid NOMA scheme is proposed in which a user can transmit signals not only by using its own time slot but also by using the time slots of other users. The data rate maximization problem is studied by optimizing the power allocation, where closed-form solutions are obtained. Further more, the conditions under which hybrid NOMA can achieve a higher instantaneous data rate with less power consumption than OMA are obtained. It is proved that the probability that hybrid NOMA can achieve a higher instantaneous data rate with less power consumption than OMA approaches one in the high SNR regime, indicating the superiority of hybrid NOMA in terms of power efficiency. Numerical results are also provided to verify the developed analysis and also to demonstrate the superior performance of hybrid NOMA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01776v1-abstract-full').style.display = 'none'; document.getElementById('2411.01776v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21897">arXiv:2410.21897</a> <span> [<a href="https://arxiv.org/pdf/2410.21897">pdf</a>, <a href="https://arxiv.org/format/2410.21897">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Semi-Supervised Self-Learning Enhanced Music Emotion Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifu Sun</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xulong Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+M">Monan Zhou</a>, <a href="/search/eess?searchtype=author&query=Li%2C+W">Wei Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.21897v1-abstract-short" style="display: inline;"> Music emotion recognition (MER) aims to identify the emotions conveyed in a given musical piece. But currently in the field of MER, the available public datasets have limited sample sizes. Recently, segment-based methods for emotion-related tasks have been proposed, which train backbone networks on shorter segments instead of entire audio clips, thereby naturally augmenting training samples withou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21897v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21897v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21897v1-abstract-full" style="display: none;"> Music emotion recognition (MER) aims to identify the emotions conveyed in a given musical piece. But currently in the field of MER, the available public datasets have limited sample sizes. Recently, segment-based methods for emotion-related tasks have been proposed, which train backbone networks on shorter segments instead of entire audio clips, thereby naturally augmenting training samples without requiring additional resources. Then, the predicted segment-level results are aggregated to obtain the entire song prediction. The most commonly used method is that segment inherits the label of the clip containing it, but music emotion is not constant during the whole clip. Doing so will introduce label noise and make the training overfit easily. To handle the noisy label issue, we propose a semi-supervised self-learning (SSSL) method, which can differentiate between samples with correct and incorrect labels in a self-learning manner, thus effectively utilizing the augmented segment-level data. Experiments on three public emotional datasets demonstrate that the proposed method can achieve better or comparable performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21897v1-abstract-full').style.display = 'none'; document.getElementById('2410.21897v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19615">arXiv:2410.19615</a> <span> [<a href="https://arxiv.org/pdf/2410.19615">pdf</a>, <a href="https://arxiv.org/format/2410.19615">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Equilibrium Adaptation-Based Control for Track Stand of Single-Track Two-Wheeled Robots </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+B">Boyi Wang</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+Y">Yang Deng</a>, <a href="/search/eess?searchtype=author&query=Jing%2C+F">Feilong Jing</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yiyong Sun</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhang Chen</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+B">Bin Liang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.19615v2-abstract-short" style="display: inline;"> Stationary balance control is challenging for single-track two-wheeled (STTW) robots due to the lack of elegant balancing mechanisms and the conflict between the limited attraction domain and external disturbances. To address the absence of balancing mechanisms, we draw inspiration from cyclists and leverage the track stand maneuver, which relies solely on steering and rear-wheel actuation. To ach… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19615v2-abstract-full').style.display = 'inline'; document.getElementById('2410.19615v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19615v2-abstract-full" style="display: none;"> Stationary balance control is challenging for single-track two-wheeled (STTW) robots due to the lack of elegant balancing mechanisms and the conflict between the limited attraction domain and external disturbances. To address the absence of balancing mechanisms, we draw inspiration from cyclists and leverage the track stand maneuver, which relies solely on steering and rear-wheel actuation. To achieve accurate tracking in the presence of matched and mismatched disturbances, we propose an equilibrium adaptation-based control (EABC) scheme that can be seamlessly integrated with standard disturbance observers and controllers. This scheme enables adaptation to slow-varying disturbances by utilizing a disturbed equilibrium estimator, effectively handling both matched and mismatched disturbances in a unified manner while ensuring accurate tracking with zero steady-state error. We integrate the EABC scheme with nonlinear model predictive control (MPC) for the track stand of STTW robots and validate its effectiveness through two experimental scenarios. Our method demonstrates significant improvements in tracking accuracy, reducing errors by several orders of magnitude. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19615v2-abstract-full').style.display = 'none'; document.getElementById('2410.19615v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 7 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18083">arXiv:2410.18083</a> <span> [<a href="https://arxiv.org/pdf/2410.18083">pdf</a>, <a href="https://arxiv.org/format/2410.18083">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> FIPER: Generalizable Factorized Fields for Joint Image Compression and Super-Resolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yang-Che Sun</a>, <a href="/search/eess?searchtype=author&query=Yeo%2C+C+Y">Cheng Yu Yeo</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+E">Ernie Chu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jun-Cheng Chen</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yu-Lun Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18083v2-abstract-short" style="display: inline;"> In this work, we propose a unified representation for Super-Resolution (SR) and Image Compression, termed Factorized Fields, motivated by the shared principles between these two tasks. Both SISR and Image Compression require recovering and preserving fine image details--whether by enhancing resolution or reconstructing compressed data. Unlike previous methods that mainly focus on network architect… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18083v2-abstract-full').style.display = 'inline'; document.getElementById('2410.18083v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18083v2-abstract-full" style="display: none;"> In this work, we propose a unified representation for Super-Resolution (SR) and Image Compression, termed Factorized Fields, motivated by the shared principles between these two tasks. Both SISR and Image Compression require recovering and preserving fine image details--whether by enhancing resolution or reconstructing compressed data. Unlike previous methods that mainly focus on network architecture, our proposed approach utilizes a basis-coefficient decomposition to explicitly capture multi-scale visual features and structural components in images, addressing the core challenges of both tasks. We first derive our SR model, which includes a Coefficient Backbone and Basis Swin Transformer for generalizable Factorized Fields. Then, to further unify these two tasks, we leverage the strong information-recovery capabilities of the trained SR modules as priors in the compression pipeline, improving both compression efficiency and detail reconstruction. Additionally, we introduce a merged-basis compression branch that consolidates shared structures, further optimizing the compression process. Extensive experiments show that our unified representation delivers state-of-the-art performance, achieving an average relative improvement of 204.4% in PSNR over the baseline in Super-Resolution (SR) and 9.35% BD-rate reduction in Image Compression compared to the previous SOTA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18083v2-abstract-full').style.display = 'none'; document.getElementById('2410.18083v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project page: https://jayisaking.github.io/FIPER/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17812">arXiv:2410.17812</a> <span> [<a href="https://arxiv.org/pdf/2410.17812">pdf</a>, <a href="https://arxiv.org/format/2410.17812">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> PGDiffSeg: Prior-Guided Denoising Diffusion Model with Parameter-Shared Attention for Breast Cancer Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Feng%2C+F">Feiyan Feng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+T">Tianyu Liu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+H">Hong Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+J">Jun Zhao</a>, <a href="/search/eess?searchtype=author&query=Li%2C+W">Wei Li</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yanshen Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.17812v1-abstract-short" style="display: inline;"> Early detection through imaging and accurate diagnosis is crucial in mitigating the high mortality rate associated with breast cancer. However, locating tumors from low-resolution and high-noise medical images is extremely challenging. Therefore, this paper proposes a novel PGDiffSeg (Prior-Guided Diffusion Denoising Model with Parameter-Shared Attention) that applies diffusion denoising methods t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17812v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17812v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17812v1-abstract-full" style="display: none;"> Early detection through imaging and accurate diagnosis is crucial in mitigating the high mortality rate associated with breast cancer. However, locating tumors from low-resolution and high-noise medical images is extremely challenging. Therefore, this paper proposes a novel PGDiffSeg (Prior-Guided Diffusion Denoising Model with Parameter-Shared Attention) that applies diffusion denoising methods to breast cancer medical image segmentation, accurately recovering the affected areas from Gaussian noise. Firstly, we design a parallel pipeline for noise processing and semantic information processing and propose a parameter-shared attention module (PSA) in multi-layer that seamlessly integrates these two pipelines. This integration empowers PGDiffSeg to incorporate semantic details at multiple levels during the denoising process, producing highly accurate segmentation maps. Secondly, we introduce a guided strategy that leverages prior knowledge to simulate the decision-making process of medical professionals, thereby enhancing the model's ability to locate tumor positions precisely. Finally, we provide the first-ever discussion on the interpretability of the generative diffusion model in the context of breast cancer segmentation. Extensive experiments have demonstrated the superiority of our model over the current state-of-the-art approaches, confirming its effectiveness as a flexible diffusion denoising method suitable for medical image research. Our code will be publicly available later. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17812v1-abstract-full').style.display = 'none'; document.getElementById('2410.17812v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08706">arXiv:2410.08706</a> <span> [<a href="https://arxiv.org/pdf/2410.08706">pdf</a>, <a href="https://arxiv.org/format/2410.08706">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Goal-Oriented Status Updating for Real-time Remote Inference over Networks with Two-Way Delay </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ari%2C+C">Cagri Ari</a>, <a href="/search/eess?searchtype=author&query=Shisher%2C+M+K+C">Md Kamran Chowdhury Shisher</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yin Sun</a>, <a href="/search/eess?searchtype=author&query=Uysal%2C+E">Elif Uysal</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.08706v3-abstract-short" style="display: inline;"> We study a setting where an intelligent model (e.g., a pre-trained neural network) predicts the real-time value of a target signal using data samples transmitted from a remote source according to a scheduling policy. The scheduler decides on i) the age of the samples to be sent, ii) when to send them, and iii) the length of each packet (i.e., the number of samples contained in each packet). The de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08706v3-abstract-full').style.display = 'inline'; document.getElementById('2410.08706v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08706v3-abstract-full" style="display: none;"> We study a setting where an intelligent model (e.g., a pre-trained neural network) predicts the real-time value of a target signal using data samples transmitted from a remote source according to a scheduling policy. The scheduler decides on i) the age of the samples to be sent, ii) when to send them, and iii) the length of each packet (i.e., the number of samples contained in each packet). The dependence of inference quality on the Age of Information (AoI) for a given packet length is modeled by a general relationship. Previous work assumed i.i.d. transmission delays with immediate feedback or were restricted to the case where inference performance degrades as the input data ages. Our formulation, in addition to capturing non-monotone age dependence, also covers Markovian delay on both forward and feedback links. We model this as an infinite-horizon average-cost Semi-Markov Decision Process. We obtain a closed-form solution that decides on (i) and (ii) for any constant packet length. The solution for when to send is an index-based threshold policy, where the index function is expressed in terms of the delay state and AoI at the receiver. The age of the packet selected is a function of the delay state. We separately optimize the value of the constant length. We also develop an index-based threshold policy for the variable length case, which allows a complexity reduction. In simulation results, we observe that our goal-oriented scheduler drops inference error down to one sixth with respect to age-based scheduling of unit-length packets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08706v3-abstract-full').style.display = 'none'; document.getElementById('2410.08706v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 9 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04225">arXiv:2410.04225</a> <span> [<a href="https://arxiv.org/pdf/2410.04225">pdf</a>, <a href="https://arxiv.org/format/2410.04225">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Molodetskikh%2C+I">Ivan Molodetskikh</a>, <a href="/search/eess?searchtype=author&query=Borisov%2C+A">Artem Borisov</a>, <a href="/search/eess?searchtype=author&query=Vatolin%2C+D">Dmitriy Vatolin</a>, <a href="/search/eess?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+J">Jianzhao Liu</a>, <a href="/search/eess?searchtype=author&query=Zhi%2C+T">Tianwu Zhi</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yabin Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yang Li</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+J">Jingwen Xu</a>, <a href="/search/eess?searchtype=author&query=Liao%2C+Y">Yiting Liao</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+Q">Qing Luo</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+A">Ao-Xiang Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+P">Peng Zhang</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+H">Haibo Lei</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+L">Linyan Jiang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yaqing Li</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+Y">Yuqin Cao</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+W">Wei Sun</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Weixia Zhang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yinan Sun</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+Z">Ziheng Jia</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+Y">Yuxin Zhu</a>, <a href="/search/eess?searchtype=author&query=Min%2C+X">Xiongkuo Min</a>, <a href="/search/eess?searchtype=author&query=Zhai%2C+G">Guangtao Zhai</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+W">Weihua Luo</a> , et al. (2 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.04225v1-abstract-short" style="display: inline;"> This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The task of this challenge was to develop an objective QA method for videos upscaled 2x and 4x by modern image- and video-SR algorithms. QA methods were evaluated by comparing their output with aggregate subjec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04225v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04225v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04225v1-abstract-full" style="display: none;"> This paper presents the Video Super-Resolution (SR) Quality Assessment (QA) Challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The task of this challenge was to develop an objective QA method for videos upscaled 2x and 4x by modern image- and video-SR algorithms. QA methods were evaluated by comparing their output with aggregate subjective scores collected from >150,000 pairwise votes obtained through crowd-sourced comparisons across 52 SR methods and 1124 upscaled videos. The goal was to advance the state-of-the-art in SR QA, which had proven to be a challenging problem with limited applicability of traditional QA methods. The challenge had 29 registered participants, and 5 teams had submitted their final results, all outperforming the current state-of-the-art. All data, including the private test subset, has been made publicly available on the challenge homepage at https://challenges.videoprocessing.ai/challenges/super-resolution-metrics-challenge.html <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04225v1-abstract-full').style.display = 'none'; document.getElementById('2410.04225v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 7 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17899">arXiv:2409.17899</a> <span> [<a href="https://arxiv.org/pdf/2409.17899">pdf</a>, <a href="https://arxiv.org/format/2409.17899">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Revisiting Acoustic Similarity in Emotional Speech and Music via Self-Supervised Representations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yujia Sun</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+Z">Zeyu Zhao</a>, <a href="/search/eess?searchtype=author&query=Richmond%2C+K">Korin Richmond</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yuanchao Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17899v1-abstract-short" style="display: inline;"> Emotion recognition from speech and music shares similarities due to their acoustic overlap, which has led to interest in transferring knowledge between these domains. However, the shared acoustic cues between speech and music, particularly those encoded by Self-Supervised Learning (SSL) models, remain largely unexplored, given the fact that SSL models for speech and music have rarely been applied… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17899v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17899v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17899v1-abstract-full" style="display: none;"> Emotion recognition from speech and music shares similarities due to their acoustic overlap, which has led to interest in transferring knowledge between these domains. However, the shared acoustic cues between speech and music, particularly those encoded by Self-Supervised Learning (SSL) models, remain largely unexplored, given the fact that SSL models for speech and music have rarely been applied in cross-domain research. In this work, we revisit the acoustic similarity between emotion speech and music, starting with an analysis of the layerwise behavior of SSL models for Speech Emotion Recognition (SER) and Music Emotion Recognition (MER). Furthermore, we perform cross-domain adaptation by comparing several approaches in a two-stage fine-tuning process, examining effective ways to utilize music for SER and speech for MER. Lastly, we explore the acoustic similarities between emotional speech and music using Frechet audio distance for individual emotions, uncovering the issue of emotion bias in both speech and music SSL models. Our findings reveal that while speech and music SSL models do capture shared acoustic features, their behaviors can vary depending on different emotions due to their training strategies and domain-specificities. Additionally, parameter-efficient fine-tuning can enhance SER and MER performance by leveraging knowledge from each other. This study provides new insights into the acoustic similarity between emotional speech and music, and highlights the potential for cross-domain generalization to improve SER and MER systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17899v1-abstract-full').style.display = 'none'; document.getElementById('2409.17899v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14400">arXiv:2409.14400</a> <span> [<a href="https://arxiv.org/pdf/2409.14400">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Preamble Design for Joint Frame Synchronization, Frequency Offset Estimation, and Channel Estimation in Upstream Burst-mode Detection of Coherent PONs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yongxin Sun</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+H">Hexun Jiang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yicheng Xu</a>, <a href="/search/eess?searchtype=author&query=Fu%2C+M">Mengfan Fu</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+Y">Yixiao Zhu</a>, <a href="/search/eess?searchtype=author&query=Yi%2C+L">Lilin Yi</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+W">Weisheng Hu</a>, <a href="/search/eess?searchtype=author&query=Zhuge%2C+Q">Qunbi Zhuge</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14400v1-abstract-short" style="display: inline;"> Coherent optics has demonstrated significant potential as a viable solution for achieving 100 Gb/s and higher speeds in single-wavelength passive optical networks (PON). However, upstream burst-mode coherent detection is a major challenge when adopting coherent optics in access networks. To accelerate digital signal processing (DSP) convergence with a minimal preamble length, we propose a novel bu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14400v1-abstract-full').style.display = 'inline'; document.getElementById('2409.14400v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14400v1-abstract-full" style="display: none;"> Coherent optics has demonstrated significant potential as a viable solution for achieving 100 Gb/s and higher speeds in single-wavelength passive optical networks (PON). However, upstream burst-mode coherent detection is a major challenge when adopting coherent optics in access networks. To accelerate digital signal processing (DSP) convergence with a minimal preamble length, we propose a novel burst-mode preamble design based on a constant amplitude zero auto-correlation sequence. This design facilitates comprehensive estimation of linear channel effects in the frequency domain, including polarization state rotation, differential group delay, chromatic dispersion, and polarization-dependent loss, providing overall system response information for channel equalization pre-convergence. Additionally, this preamble utilizes the same training unit to jointly achieve three key DSP functions: frame synchronization, frequency offset estimation, and channel estimation. This integration contributes to a significant reduction in the preamble length. The feasibility of the proposed preamble with a length of 272 symbols and corresponding DSP was experimentally verified in a 15 Gbaud coherent system using dual-polarization 16 quadrature amplitude modulation. The experimental results based on this scheme showed a superior performance of the convergence acceleration. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14400v1-abstract-full').style.display = 'none'; document.getElementById('2409.14400v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 12 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09214">arXiv:2409.09214</a> <span> [<a href="https://arxiv.org/pdf/2409.09214">pdf</a>, <a href="https://arxiv.org/format/2409.09214">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Seed-Music: A Unified Framework for High Quality and Controlled Music Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Bai%2C+Y">Ye Bai</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+H">Haonan Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jitong Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhuo Chen</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+Y">Yi Deng</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+X">Xiaohong Dong</a>, <a href="/search/eess?searchtype=author&query=Hantrakul%2C+L">Lamtharn Hantrakul</a>, <a href="/search/eess?searchtype=author&query=Hao%2C+W">Weituo Hao</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Q">Qingqing Huang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Z">Zhongyi Huang</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+D">Dongya Jia</a>, <a href="/search/eess?searchtype=author&query=La%2C+F">Feihu La</a>, <a href="/search/eess?searchtype=author&query=Le%2C+D">Duc Le</a>, <a href="/search/eess?searchtype=author&query=Li%2C+B">Bochen Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chumin Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+H">Hui Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xingxing Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shouda Liu</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+W">Wei-Tsung Lu</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+Y">Yiqing Lu</a>, <a href="/search/eess?searchtype=author&query=Shaw%2C+A">Andrew Shaw</a>, <a href="/search/eess?searchtype=author&query=Spijkervet%2C+J">Janne Spijkervet</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yakun Sun</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+B">Bo Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Ju-Chiang Wang</a> , et al. (13 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.09214v3-abstract-short" style="display: inline;"> We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music gene… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09214v3-abstract-full').style.display = 'inline'; document.getElementById('2409.09214v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09214v3-abstract-full" style="display: none;"> We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio. We encourage readers to listen to demo audio examples at https://team.doubao.com/seed-music "https://team.doubao.com/seed-music". <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09214v3-abstract-full').style.display = 'none'; document.getElementById('2409.09214v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Seed-Music technical report, 20 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.15118">arXiv:2408.15118</a> <span> [<a href="https://arxiv.org/pdf/2408.15118">pdf</a>, <a href="https://arxiv.org/format/2408.15118">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> DIFR3CT: Latent Diffusion for Probabilistic 3D CT Reconstruction from Few Planar X-Rays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yiran Sun</a>, <a href="/search/eess?searchtype=author&query=Baroudi%2C+H">Hana Baroudi</a>, <a href="/search/eess?searchtype=author&query=Netherton%2C+T">Tucker Netherton</a>, <a href="/search/eess?searchtype=author&query=Court%2C+L">Laurence Court</a>, <a href="/search/eess?searchtype=author&query=Mawlawi%2C+O">Osama Mawlawi</a>, <a href="/search/eess?searchtype=author&query=Veeraraghavan%2C+A">Ashok Veeraraghavan</a>, <a href="/search/eess?searchtype=author&query=Balakrishnan%2C+G">Guha Balakrishnan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.15118v1-abstract-short" style="display: inline;"> Computed Tomography (CT) scans are the standard-of-care for the visualization and diagnosis of many clinical ailments, and are needed for the treatment planning of external beam radiotherapy. Unfortunately, the availability of CT scanners in low- and mid-resource settings is highly variable. Planar x-ray radiography units, in comparison, are far more prevalent, but can only provide limited 2D obse… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15118v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15118v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15118v1-abstract-full" style="display: none;"> Computed Tomography (CT) scans are the standard-of-care for the visualization and diagnosis of many clinical ailments, and are needed for the treatment planning of external beam radiotherapy. Unfortunately, the availability of CT scanners in low- and mid-resource settings is highly variable. Planar x-ray radiography units, in comparison, are far more prevalent, but can only provide limited 2D observations of the 3D anatomy. In this work we propose DIFR3CT, a 3D latent diffusion model, that can generate a distribution of plausible CT volumes from one or few (<10) planar x-ray observations. DIFR3CT works by fusing 2D features from each x-ray into a joint 3D space, and performing diffusion conditioned on these fused features in a low-dimensional latent space. We conduct extensive experiments demonstrating that DIFR3CT is better than recent sparse CT reconstruction baselines in terms of standard pixel-level (PSNR, SSIM) on both the public LIDC and in-house post-mastectomy CT datasets. We also show that DIFR3CT supports uncertainty quantification via Monte Carlo sampling, which provides an opportunity to measure reconstruction reliability. Finally, we perform a preliminary pilot study evaluating DIFR3CT for automated breast radiotherapy contouring and planning -- and demonstrate promising feasibility. Our code is available at https://github.com/yransun/DIFR3CT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15118v1-abstract-full').style.display = 'none'; document.getElementById('2408.15118v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 9 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.15069">arXiv:2408.15069</a> <span> [<a href="https://arxiv.org/pdf/2408.15069">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Instrumentation and Detectors">physics.ins-det</span> </div> </div> <p class="title is-5 mathjax"> Geometric Artifact Correction for Symmetric Multi-Linear Trajectory CT: Theory, Method, and Generalization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zhisheng Wang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yanxu Sun</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shangyu Li</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+L">Legeng Lin</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shunli Wang</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+J">Junning Cui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.15069v1-abstract-short" style="display: inline;"> For extending CT field-of-view to perform non-destructive testing, the Symmetric Multi-Linear trajectory Computed Tomography (SMLCT) has been developed as a successful example of non-standard CT scanning modes. However, inevitable geometric errors can cause severe artifacts in the reconstructed images. The existing calibration method for SMLCT is both crude and inefficient. It involves reconstruct… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15069v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15069v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15069v1-abstract-full" style="display: none;"> For extending CT field-of-view to perform non-destructive testing, the Symmetric Multi-Linear trajectory Computed Tomography (SMLCT) has been developed as a successful example of non-standard CT scanning modes. However, inevitable geometric errors can cause severe artifacts in the reconstructed images. The existing calibration method for SMLCT is both crude and inefficient. It involves reconstructing hundreds of images by exhaustively substituting each potential error, and then manually identifying the images with the fewest geometric artifacts to estimate the final geometric errors for calibration. In this paper, we comprehensively and efficiently address the challenging geometric artifacts in SMLCT, , and the corresponding works mainly involve theory, method, and generalization. In particular, after identifying sensitive parameters and conducting some theory analysis of geometric artifacts, we summarize several key properties between sensitive geometric parameters and artifact characteristics. Then, we further construct mathematical relationships that relate sensitive geometric errors to the pixel offsets of reconstruction images with artifact characteristics. To accurately extract pixel bias, we innovatively adapt the Generalized Cross-Correlation with Phase Transform (GCC-PHAT) algorithm, commonly used in sound processing, for our image registration task for each paired symmetric LCT. This adaptation leads to the design of a highly efficient rigid translation registration method. Simulation and physical experiments have validated the excellent performance of this work. Additionally, our results demonstrate significant generalization to common rotated CT and a variant of SMLCT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15069v1-abstract-full').style.display = 'none'; document.getElementById('2408.15069v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 10 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68U10 (Primary) 68V99; 68Q30(Secondary) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13716">arXiv:2408.13716</a> <span> [<a href="https://arxiv.org/pdf/2408.13716">pdf</a>, <a href="https://arxiv.org/format/2408.13716">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> FreqINR: Frequency Consistency for Implicit Neural Representation with Adaptive DCT Frequency Loss </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wei%2C+M">Meiyi Wei</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+L">Liu Xie</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Ying Sun</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+G">Gang Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.13716v1-abstract-short" style="display: inline;"> Recent advancements in local Implicit Neural Representation (INR) demonstrate its exceptional capability in handling images at various resolutions. However, frequency discrepancies between high-resolution (HR) and ground-truth images, especially at larger scales, result in significant artifacts and blurring in HR images. This paper introduces Frequency Consistency for Implicit Neural Representatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13716v1-abstract-full').style.display = 'inline'; document.getElementById('2408.13716v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13716v1-abstract-full" style="display: none;"> Recent advancements in local Implicit Neural Representation (INR) demonstrate its exceptional capability in handling images at various resolutions. However, frequency discrepancies between high-resolution (HR) and ground-truth images, especially at larger scales, result in significant artifacts and blurring in HR images. This paper introduces Frequency Consistency for Implicit Neural Representation (FreqINR), an innovative Arbitrary-scale Super-resolution method aimed at enhancing detailed textures by ensuring spectral consistency throughout both training and inference. During training, we employ Adaptive Discrete Cosine Transform Frequency Loss (ADFL) to minimize the frequency gap between HR and ground-truth images, utilizing 2-Dimensional DCT bases and focusing dynamically on challenging frequencies. During inference, we extend the receptive field to preserve spectral coherence between low-resolution (LR) and ground-truth images, which is crucial for the model to generate high-frequency details from LR counterparts. Experimental results show that FreqINR, as a lightweight approach, achieves state-of-the-art performance compared to existing Arbitrary-scale Super-resolution methods and offers notable improvements in computational efficiency. The code for our method will be made publicly available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13716v1-abstract-full').style.display = 'none'; document.getElementById('2408.13716v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages, 7 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.11982">arXiv:2408.11982</a> <span> [<a href="https://arxiv.org/pdf/2408.11982">pdf</a>, <a href="https://arxiv.org/format/2408.11982">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Smirnov%2C+M">Maksim Smirnov</a>, <a href="/search/eess?searchtype=author&query=Gushchin%2C+A">Aleksandr Gushchin</a>, <a href="/search/eess?searchtype=author&query=Antsiferova%2C+A">Anastasia Antsiferova</a>, <a href="/search/eess?searchtype=author&query=Vatolin%2C+D">Dmitry Vatolin</a>, <a href="/search/eess?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+Z">Ziheng Jia</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zicheng Zhang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+W">Wei Sun</a>, <a href="/search/eess?searchtype=author&query=Qian%2C+J">Jiaying Qian</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+Y">Yuqin Cao</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yinan Sun</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+Y">Yuxin Zhu</a>, <a href="/search/eess?searchtype=author&query=Min%2C+X">Xiongkuo Min</a>, <a href="/search/eess?searchtype=author&query=Zhai%2C+G">Guangtao Zhai</a>, <a href="/search/eess?searchtype=author&query=De%2C+K">Kanjar De</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+Q">Qing Luo</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+A">Ao-Xiang Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+P">Peng Zhang</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+H">Haibo Lei</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+L">Linyan Jiang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yaqing Li</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+W">Wenhui Meng</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhenzhong Chen</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+Z">Zhengxue Cheng</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+J">Jiahao Xiao</a> , et al. (7 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.11982v3-abstract-short" style="display: inline;"> Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11982v3-abstract-full').style.display = 'inline'; document.getElementById('2408.11982v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.11982v3-abstract-full" style="display: none;"> Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11982v3-abstract-full').style.display = 'none'; document.getElementById('2408.11982v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.07820">arXiv:2408.07820</a> <span> [<a href="https://arxiv.org/pdf/2408.07820">pdf</a>, <a href="https://arxiv.org/format/2408.07820">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Hybrid Semantic/Bit Communication Based Networking Problem Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xia%2C+L">Le Xia</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yao Sun</a>, <a href="/search/eess?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Lan Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Lei Zhang</a>, <a href="/search/eess?searchtype=author&query=Imran%2C+M+A">Muhammad Ali Imran</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.07820v2-abstract-short" style="display: inline;"> This paper jointly investigates user association (UA), mode selection (MS), and bandwidth allocation (BA) problems in a novel and practical next-generation cellular network where two modes of semantic communication (SemCom) and conventional bit communication (BitCom) coexist, namely hybrid semantic/bit communication network (HSB-Net). Concretely, we first identify a unified performance metric of m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07820v2-abstract-full').style.display = 'inline'; document.getElementById('2408.07820v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.07820v2-abstract-full" style="display: none;"> This paper jointly investigates user association (UA), mode selection (MS), and bandwidth allocation (BA) problems in a novel and practical next-generation cellular network where two modes of semantic communication (SemCom) and conventional bit communication (BitCom) coexist, namely hybrid semantic/bit communication network (HSB-Net). Concretely, we first identify a unified performance metric of message throughput for both SemCom and BitCom links. Next, we comprehensively develop a knowledge matching-aware two-stage tandem packet queuing model and theoretically derive the average packet loss ratio and queuing latency. Combined with several practical constraints, we then formulate a joint optimization problem for UA, MS, and BA to maximize the overall message throughput of HSB-Net. Afterward, we propose an optimal resource management strategy by employing a Lagrange primal-dual method and devising a preference list-based heuristic algorithm. Finally, numerical results validate the performance superiority of our proposed strategy compared with different benchmarks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07820v2-abstract-full').style.display = 'none'; document.getElementById('2408.07820v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been accepted for publication and will be presented in 2024 IEEE Global Communications Conference (GlobeCom 2024). arXiv admin note: substantial text overlap with arXiv:2404.04162</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.07341">arXiv:2408.07341</a> <span> [<a href="https://arxiv.org/pdf/2408.07341">pdf</a>, <a href="https://arxiv.org/format/2408.07341">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Robust Semi-supervised Multimodal Medical Image Segmentation via Cross Modality Collaboration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhou%2C+X">Xiaogen Zhou</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yiyou Sun</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+M">Min Deng</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+W+C+W">Winnie Chiu Wing Chu</a>, <a href="/search/eess?searchtype=author&query=Dou%2C+Q">Qi Dou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.07341v2-abstract-short" style="display: inline;"> Multimodal learning leverages complementary information derived from different modalities, thereby enhancing performance in medical image segmentation. However, prevailing multimodal learning methods heavily rely on extensive well-annotated data from various modalities to achieve accurate segmentation performance. This dependence often poses a challenge in clinical settings due to limited availabi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07341v2-abstract-full').style.display = 'inline'; document.getElementById('2408.07341v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.07341v2-abstract-full" style="display: none;"> Multimodal learning leverages complementary information derived from different modalities, thereby enhancing performance in medical image segmentation. However, prevailing multimodal learning methods heavily rely on extensive well-annotated data from various modalities to achieve accurate segmentation performance. This dependence often poses a challenge in clinical settings due to limited availability of such data. Moreover, the inherent anatomical misalignment between different imaging modalities further complicates the endeavor to enhance segmentation performance. To address this problem, we propose a novel semi-supervised multimodal segmentation framework that is robust to scarce labeled data and misaligned modalities. Our framework employs a novel cross modality collaboration strategy to distill modality-independent knowledge, which is inherently associated with each modality, and integrates this information into a unified fusion layer for feature amalgamation. With a channel-wise semantic consistency loss, our framework ensures alignment of modality-independent information from a feature-wise perspective across modalities, thereby fortifying it against misalignments in multimodal scenarios. Furthermore, our framework effectively integrates contrastive consistent learning to regulate anatomical structures, facilitating anatomical-wise prediction alignment on unlabeled data in semi-supervised segmentation tasks. Our method achieves competitive performance compared to other multimodal methods across three tasks: cardiac, abdominal multi-organ, and thyroid-associated orbitopathy segmentations. It also demonstrates outstanding robustness in scenarios involving scarce labeled data and misaligned modalities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07341v2-abstract-full').style.display = 'none'; document.getElementById('2408.07341v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.05705">arXiv:2408.05705</a> <span> [<a href="https://arxiv.org/pdf/2408.05705">pdf</a>, <a href="https://arxiv.org/format/2408.05705">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> TC-KANRecon: High-Quality and Accelerated MRI Reconstruction via Adaptive KAN Mechanisms and Intelligent Feature Scaling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ge%2C+R">Ruiquan Ge</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xiao Yu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Yifei Chen</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+G">Guanyu Zhou</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+F">Fan Jia</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+S">Shenghao Zhu</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+J">Junhao Jia</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+C">Chenyan Zhang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yifei Sun</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+D">Dong Zeng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Changmiao Wang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qiegen Liu</a>, <a href="/search/eess?searchtype=author&query=Niu%2C+S">Shanzhou Niu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.05705v2-abstract-short" style="display: inline;"> Magnetic Resonance Imaging (MRI) has become essential in clinical diagnosis due to its high resolution and multiple contrast mechanisms. However, the relatively long acquisition time limits its broader application. To address this issue, this study presents an innovative conditional guided diffusion model, named as TC-KANRecon, which incorporates the Multi-Free U-KAN (MF-UKAN) module and a dynamic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05705v2-abstract-full').style.display = 'inline'; document.getElementById('2408.05705v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.05705v2-abstract-full" style="display: none;"> Magnetic Resonance Imaging (MRI) has become essential in clinical diagnosis due to its high resolution and multiple contrast mechanisms. However, the relatively long acquisition time limits its broader application. To address this issue, this study presents an innovative conditional guided diffusion model, named as TC-KANRecon, which incorporates the Multi-Free U-KAN (MF-UKAN) module and a dynamic clipping strategy. TC-KANRecon model aims to accelerate the MRI reconstruction process through deep learning methods while maintaining the quality of the reconstructed images. The MF-UKAN module can effectively balance the tradeoff between image denoising and structure preservation. Specifically, it presents the multi-head attention mechanisms and scalar modulation factors, which significantly enhances the model's robustness and structure preservation capabilities in complex noise environments. Moreover, the dynamic clipping strategy in TC-KANRecon adjusts the cropping interval according to the sampling steps, thereby mitigating image detail loss typicalching the visual features of the images. Furthermore, the MC-Model incorporates full-sampling k-space information, realizing efficient fusion of conditional information, enhancing the model's ability to process complex data, and improving the realism and detail richness of reconstructed images. Experimental results demonstrate that the proposed method outperforms other MRI reconstruction methods in both qualitative and quantitative evaluations. Notably, TC-KANRecon method exhibits excellent reconstruction results when processing high-noise, low-sampling-rate MRI data. Our source code is available at https://github.com/lcbkmm/TC-KANRecon. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.05705v2-abstract-full').style.display = 'none'; document.getElementById('2408.05705v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 3 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.03055">arXiv:2408.03055</a> <span> [<a href="https://arxiv.org/pdf/2408.03055">pdf</a>, <a href="https://arxiv.org/format/2408.03055">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> FDA Jamming Against Airborne Phased-MIMO Radar-Part II: Jamming STAP Performance Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yan Sun</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wen-qin Wang</a>, <a href="/search/eess?searchtype=author&query=He%2C+Z">Zhou He</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shunsheng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.03055v1-abstract-short" style="display: inline;"> The first part of this series introduced the effectiveness of frequency diverse array (FDA) jamming through direct wave propagation in countering airborne phased multiple-input multiple-output (Phased-MIMO) radar. This part focuses on the effectiveness of FDA scattered wave (FDA-SW) jamming on the space-time adaptive processing (STAP) for airborne phased-MIMO radar. Distinguished from the clutter… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03055v1-abstract-full').style.display = 'inline'; document.getElementById('2408.03055v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.03055v1-abstract-full" style="display: none;"> The first part of this series introduced the effectiveness of frequency diverse array (FDA) jamming through direct wave propagation in countering airborne phased multiple-input multiple-output (Phased-MIMO) radar. This part focuses on the effectiveness of FDA scattered wave (FDA-SW) jamming on the space-time adaptive processing (STAP) for airborne phased-MIMO radar. Distinguished from the clutter signals, the ground equidistant scatterers of FDA-SW jamming constitute an elliptical ring, whose trajectory equations are mathematically derived to further determine the spatial frequency and Doppler frequency. For the phased-MIMO radar with different transmitting partitions, the effects of jamming frequency offset of FDA-SW on the clutter rank and STAP performance are discussed. Theoretical analysis provides the variation interval of clutter rank and the relationship between the jamming frequency offset and the improvement factor (IF) notch of phased-MIMO-STAP. Importantly, the requirements of jamming frequency offset for both two-part applications are discussed in this part. Numerical results verify these mathematical findings and validate the effectiveness of the proposed FDA jamming in countering the phased-MIMO radar. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03055v1-abstract-full').style.display = 'none'; document.getElementById('2408.03055v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.03050">arXiv:2408.03050</a> <span> [<a href="https://arxiv.org/pdf/2408.03050">pdf</a>, <a href="https://arxiv.org/format/2408.03050">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> FDA Jamming Against Airborne Phased-MIMO Radar-Part I: Matched Filtering and Spatial Filtering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yan Sun</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wen-qin Wang</a>, <a href="/search/eess?searchtype=author&query=He%2C+Z">Zhou He</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shunsheng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.03050v1-abstract-short" style="display: inline;"> Phased multiple-input multiple-output (Phased-MIMO) radar has received increasing attention for enjoying the advantages of waveform diversity and range-dependency from frequency diverse array MIMO (FDA-MIMO) radar without sacrificing coherent processing gain through partitioning transmit subarray. This two-part series proposes a framework of electronic countermeasures (ECM) inspired by frequency d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03050v1-abstract-full').style.display = 'inline'; document.getElementById('2408.03050v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.03050v1-abstract-full" style="display: none;"> Phased multiple-input multiple-output (Phased-MIMO) radar has received increasing attention for enjoying the advantages of waveform diversity and range-dependency from frequency diverse array MIMO (FDA-MIMO) radar without sacrificing coherent processing gain through partitioning transmit subarray. This two-part series proposes a framework of electronic countermeasures (ECM) inspired by frequency diverse array (FDA) radar, called FDA jamming, evaluating its effectiveness for countering airborne phased-MIMO radar. This part introduces the principles and categories of FDA jammer and proposes the FDA jamming signal model based on the two cases of phased-MIMO radar, phased-array (PA) radar and FDA-MIMO radar. Moreover, the effects of FDA jamming on matched filtering and spatial filtering of PA and FDA-MIMO radar are analyzed. Numerical results verify the theoretical analysis and validate the effectiveness of the proposed FDA jamming in countering phased-MIMO radar. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03050v1-abstract-full').style.display = 'none'; document.getElementById('2408.03050v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.03045">arXiv:2408.03045</a> <span> [<a href="https://arxiv.org/pdf/2408.03045">pdf</a>, <a href="https://arxiv.org/format/2408.03045">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Coherent FDA Radar: Transmitter and Receiver Design and Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yan Sun</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+M">Ming-jie Jia</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wen-qin Wang</a>, <a href="/search/eess?searchtype=author&query=Greco%2C+M+S">Maria Sabrina Greco</a>, <a href="/search/eess?searchtype=author&query=Gini%2C+F">Fulvio Gini</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shunsheng Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.03045v1-abstract-short" style="display: inline;"> The combination of frequency diverse array (FDA) radar technology with the multiple input multiple output (MIMO) radar architecture and waveform diversity techniques potentially promises a high integration gain with respect to conventional phased array (PA) radars. In this paper, we propose an approach to the design of the transmitter and the receiver of a coherent FDA (C-FDA) radar, that enables… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03045v1-abstract-full').style.display = 'inline'; document.getElementById('2408.03045v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.03045v1-abstract-full" style="display: none;"> The combination of frequency diverse array (FDA) radar technology with the multiple input multiple output (MIMO) radar architecture and waveform diversity techniques potentially promises a high integration gain with respect to conventional phased array (PA) radars. In this paper, we propose an approach to the design of the transmitter and the receiver of a coherent FDA (C-FDA) radar, that enables it to perform the demodulation with spectral overlapping, due to the small frequency offset. To this purpose, we derive the generalized space-time-range signal model and we prove that the proposed C-FDA radar has a higher coherent array gain than a PA radar, and at the same time, it effectively resolves the secondary range-ambiguous (SRA) problem of FDA-MIMO radar, allowing for mainlobe interference suppression and range-ambiguous clutter suppression. Numerical analysis results prove the effectiveness of the proposed C-FDA radar in terms on anti-interference and anti-clutter capabilities over conventional radars. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.03045v1-abstract-full').style.display = 'none'; document.getElementById('2408.03045v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.02025">arXiv:2408.02025</a> <span> [<a href="https://arxiv.org/pdf/2408.02025">pdf</a>, <a href="https://arxiv.org/format/2408.02025">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Contrastive Learning-based Chaining-Cluster for Multilingual Voice-Face Association </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+W">Wuyang Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yanjie Sun</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+K">Kele Xu</a>, <a href="/search/eess?searchtype=author&query=Dou%2C+Y">Yong Dou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.02025v2-abstract-short" style="display: inline;"> The innate correlation between a person's face and voice has recently emerged as a compelling area of study, especially within the context of multilingual environments. This paper introduces our novel solution to the Face-Voice Association in Multilingual Environments (FAME) 2024 challenge, focusing on a contrastive learning-based chaining-cluster method to enhance face-voice association. This tas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02025v2-abstract-full').style.display = 'inline'; document.getElementById('2408.02025v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.02025v2-abstract-full" style="display: none;"> The innate correlation between a person's face and voice has recently emerged as a compelling area of study, especially within the context of multilingual environments. This paper introduces our novel solution to the Face-Voice Association in Multilingual Environments (FAME) 2024 challenge, focusing on a contrastive learning-based chaining-cluster method to enhance face-voice association. This task involves the challenges of building biometric relations between auditory and visual modality cues and modelling the prosody interdependence between different languages while addressing both intrinsic and extrinsic variability present in the data. To handle these non-trivial challenges, our method employs supervised cross-contrastive (SCC) learning to establish robust associations between voices and faces in multi-language scenarios. Following this, we have specifically designed a chaining-cluster-based post-processing step to mitigate the impact of outliers often found in unconstrained in the wild data. We conducted extensive experiments to investigate the impact of language on face-voice association. The overall results were evaluated on the FAME public evaluation platform, where we achieved 2nd place. The results demonstrate the superior performance of our method, and we validate the robustness and effectiveness of our proposed approach. Code is available at https://github.com/colaudiolab/FAME24_solution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02025v2-abstract-full').style.display = 'none'; document.getElementById('2408.02025v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.19709">arXiv:2407.19709</a> <span> [<a href="https://arxiv.org/pdf/2407.19709">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> The Family of LML Detectors and the Family of LAS Detectors for Massive MIMO Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yi Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.19709v3-abstract-short" style="display: inline;"> The family of local maximum likelihood (LML) detectors, including the global maximum likelihood (GML) detector, and the family of likelihood ascent search (LAS) detectors are akin to each other and possess common properties significant in both theory and practical multi-input multi-output (MIMO) communications. It is proved that a large MIMO channel possesses the LML characteristic, implying and p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.19709v3-abstract-full').style.display = 'inline'; document.getElementById('2407.19709v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.19709v3-abstract-full" style="display: none;"> The family of local maximum likelihood (LML) detectors, including the global maximum likelihood (GML) detector, and the family of likelihood ascent search (LAS) detectors are akin to each other and possess common properties significant in both theory and practical multi-input multi-output (MIMO) communications. It is proved that a large MIMO channel possesses the LML characteristic, implying and predicting that a local search detector with likelihood ascent, like a wide-sense sequential LAS (WSLAS) detector, can approach the GML detection. By the replica method, the bit error rate (BER) of an LML detector in the large MIMO channel is obtained. The BER indicates that in the high signal-to-noise ratio (SNR) regime, both the LML and GML detectors achieve the AWGN channel performance when the channel load is as high as up to 1.5086 bits/dimension with an equal-energy distribution, and the channel load can be higher with an unequal-energy distribution. The analytical result is verified by simulation in the equal-energy distribution that the sequential LAS (SLAS) detector, a linear-complexity LML detector, can approach the BER of the NP-hard GML detector. The LML and LAS detectors in the two families are successfully applied to symbol detection in massive antenna MIMO communications and demonstrate the performance near the GML detection. This book chapter reviews the LML and LAS detectors in a unified framework. The focus is on their formulation, relationships, properties, and GML performance in BER and spectral efficiency in large MIMO channels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.19709v3-abstract-full').style.display = 'none'; document.getElementById('2407.19709v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">28 pages, 6 figures</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+Y&start=300" class="pagination-link " aria-label="Page 7" aria-current="page">7 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository