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 1–45 of 45 results for author: <span class="mathjax">Yan, C</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=Yan%2C+C">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="Yan, C"> </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=Yan%2C+C&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="Yan, C"> <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> <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/2502.11946">arXiv:2502.11946</a> <span> [<a href="https://arxiv.org/pdf/2502.11946">pdf</a>, <a href="https://arxiv.org/format/2502.11946">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</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"> Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huang%2C+A">Ailin Huang</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+B">Boyong Wu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+B">Bruce Wang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+C">Chen Hu</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+C">Chengli Feng</a>, <a href="/search/eess?searchtype=author&query=Tian%2C+F">Fei Tian</a>, <a href="/search/eess?searchtype=author&query=Shen%2C+F">Feiyu Shen</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jingbei Li</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+M">Mingrui Chen</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+P">Peng Liu</a>, <a href="/search/eess?searchtype=author&query=Miao%2C+R">Ruihang Miao</a>, <a href="/search/eess?searchtype=author&query=You%2C+W">Wang You</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xi Chen</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+X">Xuerui Yang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Y">Yechang Huang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yuxiang Zhang</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+Z">Zheng Gong</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zixin Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+H">Hongyu Zhou</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+J">Jianjian Sun</a>, <a href="/search/eess?searchtype=author&query=Li%2C+B">Brian Li</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+C">Chengting Feng</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+C">Changyi Wan</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+H">Hanpeng Hu</a> , et al. (120 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="2502.11946v2-abstract-short" style="display: inline;"> Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic control, and limited intelligence. To address these challenges, this paper introduces Step-Audio, the first production-ready open-source solution. Key contribu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11946v2-abstract-full').style.display = 'inline'; document.getElementById('2502.11946v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11946v2-abstract-full" style="display: none;"> Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic control, and limited intelligence. To address these challenges, this paper introduces Step-Audio, the first production-ready open-source solution. Key contributions include: 1) a 130B-parameter unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex tasks effectively. Based on our new StepEval-Audio-360 evaluation benchmark, Step-Audio achieves state-of-the-art performance in human evaluations, especially in terms of instruction following. On open-source benchmarks like LLaMA Question, shows 9.3% average performance improvement, demonstrating our commitment to advancing the development of open-source multi-modal language technologies. Our code and models are available at https://github.com/stepfun-ai/Step-Audio. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11946v2-abstract-full').style.display = 'none'; document.getElementById('2502.11946v2-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 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/2501.00053">arXiv:2501.00053</a> <span> [<a href="https://arxiv.org/pdf/2501.00053">pdf</a>, <a href="https://arxiv.org/format/2501.00053">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Implementing Trust in Non-Small Cell Lung Cancer Diagnosis with a Conformalized Uncertainty-Aware AI Framework in Whole-Slide Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xiaoge Zhang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+T">Tao Wang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Najdawi%2C+F">Fedaa Najdawi</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+K">Kai Zhou</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+Y">Yuan Ma</a>, <a href="/search/eess?searchtype=author&query=Cheung%2C+Y">Yiu-ming Cheung</a>, <a href="/search/eess?searchtype=author&query=Malin%2C+B+A">Bradley A. Malin</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="2501.00053v1-abstract-short" style="display: inline;"> Ensuring trustworthiness is fundamental to the development of artificial intelligence (AI) that is considered societally responsible, particularly in cancer diagnostics, where a misdiagnosis can have dire consequences. Current digital pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00053v1-abstract-full').style.display = 'inline'; document.getElementById('2501.00053v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.00053v1-abstract-full" style="display: none;"> Ensuring trustworthiness is fundamental to the development of artificial intelligence (AI) that is considered societally responsible, particularly in cancer diagnostics, where a misdiagnosis can have dire consequences. Current digital pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. To address this issue, we developed TRUECAM, a framework designed to ensure both data and model trustworthiness in non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates 1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs and 2) an ambiguity-guided elimination of tiles to filter out highly ambiguous regions, addressing data trustworthiness, as well as 3) conformal prediction to ensure controlled error rates. We systematically evaluated the framework across multiple large-scale cancer datasets, leveraging both task-specific and foundation models, illustrate that an AI model wrapped with TRUECAM significantly outperforms models that lack such guidance, in terms of classification accuracy, robustness, interpretability, and data efficiency, while also achieving improvements in fairness. These findings highlight TRUECAM as a versatile wrapper framework for digital pathology AI models with diverse architectural designs, promoting their responsible and effective applications in real-world settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00053v1-abstract-full').style.display = 'none'; document.getElementById('2501.00053v1-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 December, 2024; <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/2410.13454">arXiv:2410.13454</a> <span> [<a href="https://arxiv.org/pdf/2410.13454">pdf</a>, <a href="https://arxiv.org/ps/2410.13454">ps</a>, <a href="https://arxiv.org/format/2410.13454">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="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Byzantine-Resilient Output Optimization of Multiagent via Self-Triggered Hybrid Detection Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenhang Yan</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+L">Liping Yan</a>, <a href="/search/eess?searchtype=author&query=Lv%2C+Y">Yuezu Lv</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+B">Bolei Dong</a>, <a href="/search/eess?searchtype=author&query=Xia%2C+Y">Yuanqing Xia</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="2410.13454v1-abstract-short" style="display: inline;"> How to achieve precise distributed optimization despite unknown attacks, especially the Byzantine attacks, is one of the critical challenges for multiagent systems. This paper addresses a distributed resilient optimization for linear heterogeneous multi-agent systems faced with adversarial threats. We establish a framework aimed at realizing resilient optimization for continuous-time systems by in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13454v1-abstract-full').style.display = 'inline'; document.getElementById('2410.13454v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13454v1-abstract-full" style="display: none;"> How to achieve precise distributed optimization despite unknown attacks, especially the Byzantine attacks, is one of the critical challenges for multiagent systems. This paper addresses a distributed resilient optimization for linear heterogeneous multi-agent systems faced with adversarial threats. We establish a framework aimed at realizing resilient optimization for continuous-time systems by incorporating a novel self-triggered hybrid detection approach. The proposed hybrid detection approach is able to identify attacks on neighbors using both error thresholds and triggering intervals, thereby optimizing the balance between effective attack detection and the reduction of excessive communication triggers. Through using an edge-based adaptive self-triggered approach, each agent can receive its neighbors' information and determine whether these information is valid. If any neighbor prove invalid, each normal agent will isolate that neighbor by disconnecting communication along that specific edge. Importantly, our adaptive algorithm guarantees the accuracy of the optimization solution even when an agent is isolated by its neighbors. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13454v1-abstract-full').style.display = 'none'; document.getElementById('2410.13454v1-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 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/2409.17907">arXiv:2409.17907</a> <span> [<a href="https://arxiv.org/pdf/2409.17907">pdf</a>, <a href="https://arxiv.org/format/2409.17907">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="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.14722/ndss.2025.23997">10.14722/ndss.2025.23997 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> PhantomLiDAR: Cross-modality Signal Injection Attacks against LiDAR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jin%2C+Z">Zizhi Jin</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+Q">Qinhong Jiang</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+X">Xuancun Lu</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chen Yan</a>, <a href="/search/eess?searchtype=author&query=Ji%2C+X">Xiaoyu Ji</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+W">Wenyuan Xu</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="2409.17907v1-abstract-short" style="display: inline;"> LiDAR (Light Detection and Ranging) is a pivotal sensor for autonomous driving, offering precise 3D spatial information. Previous signal attacks against LiDAR systems mainly exploit laser signals. In this paper, we investigate the possibility of cross-modality signal injection attacks, i.e., injecting intentional electromagnetic interference (IEMI) to manipulate LiDAR output. Our insight is that t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17907v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17907v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17907v1-abstract-full" style="display: none;"> LiDAR (Light Detection and Ranging) is a pivotal sensor for autonomous driving, offering precise 3D spatial information. Previous signal attacks against LiDAR systems mainly exploit laser signals. In this paper, we investigate the possibility of cross-modality signal injection attacks, i.e., injecting intentional electromagnetic interference (IEMI) to manipulate LiDAR output. Our insight is that the internal modules of a LiDAR, i.e., the laser receiving circuit, the monitoring sensors, and the beam-steering modules, even with strict electromagnetic compatibility (EMC) testing, can still couple with the IEMI attack signals and result in the malfunction of LiDAR systems. Based on the above attack surfaces, we propose the PhantomLiDAR attack, which manipulates LiDAR output in terms of Points Interference, Points Injection, Points Removal, and even LiDAR Power-Off. We evaluate and demonstrate the effectiveness of PhantomLiDAR with both simulated and real-world experiments on five COTS LiDAR systems. We also conduct feasibility experiments in real-world moving scenarios. We provide potential defense measures that can be implemented at both the sensor level and the vehicle system level to mitigate the risks associated with IEMI attacks. Video demonstrations can be viewed at https://sites.google.com/view/phantomlidar. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17907v1-abstract-full').style.display = 'none'; document.getElementById('2409.17907v1-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/2409.13398">arXiv:2409.13398</a> <span> [<a href="https://arxiv.org/pdf/2409.13398">pdf</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"> Unsourced Sparse Multiple Access foUnsourced Sparse Multiple Access for 6G Massive Communicationr 6G Massive Communication </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yuan%2C+Y">Yifei Yuan</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Y">Yuhong Huang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chunlin Yan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Sen Wang</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+S">Shuai Ma</a>, <a href="/search/eess?searchtype=author&query=Shen%2C+X">Xiaodong Shen</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="2409.13398v2-abstract-short" style="display: inline;"> Massive communication is one of key scenarios of 6G where two magnitude higher connection density would be required to serve diverse services. As a promising direction, unsourced multiple access has been proved to outperform significantly over orthogonal multiple access (OMA) or slotted-ALOHA in massive connections. In this paper we describe a design framework of unsourced sparse multiple access (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13398v2-abstract-full').style.display = 'inline'; document.getElementById('2409.13398v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.13398v2-abstract-full" style="display: none;"> Massive communication is one of key scenarios of 6G where two magnitude higher connection density would be required to serve diverse services. As a promising direction, unsourced multiple access has been proved to outperform significantly over orthogonal multiple access (OMA) or slotted-ALOHA in massive connections. In this paper we describe a design framework of unsourced sparse multiple access (USMA) that consists of two key modules: compressed sensing for preamble generation, and sparse interleaver division multiple access (SIDMA) for main packet transmission. Simulation results of general design of USMA show that the theoretical bound can be approached within 1~1.5 dB by using simple channel codes like convolutional. To illustrate the scalability of USMA, a customized design for ambient Internet of Things (A-IoT) is proposed, so that much less memory and computation are required. Simulations results of Rayleigh fading and realistic channel estimation show that USMA based A-IoT solution can deliver nearly 4 times capacity and 6 times efficiency for random access over traditional radio frequency identification (RFID) technology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13398v2-abstract-full').style.display = 'none'; document.getElementById('2409.13398v2-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 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">7 pages, 5 figures and 1 table</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09272">arXiv:2409.09272</a> <span> [<a href="https://arxiv.org/pdf/2409.09272">pdf</a>, <a href="https://arxiv.org/format/2409.09272">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</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="Multimedia">cs.MM</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"> SafeEar: Content Privacy-Preserving Audio Deepfake Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+X">Xinfeng Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+K">Kai Li</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+Y">Yifan Zheng</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chen Yan</a>, <a href="/search/eess?searchtype=author&query=Ji%2C+X">Xiaoyu Ji</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+W">Wenyuan Xu</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="2409.09272v1-abstract-short" style="display: inline;"> Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals. Existing countermeasures largely focus on determining the genuineness of speech based on complete original audio recordings, which however often contain private con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09272v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09272v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09272v1-abstract-full" style="display: none;"> Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals. Existing countermeasures largely focus on determining the genuineness of speech based on complete original audio recordings, which however often contain private content. This oversight may refrain deepfake detection from many applications, particularly in scenarios involving sensitive information like business secrets. In this paper, we propose SafeEar, a novel framework that aims to detect deepfake audios without relying on accessing the speech content within. Our key idea is to devise a neural audio codec into a novel decoupling model that well separates the semantic and acoustic information from audio samples, and only use the acoustic information (e.g., prosody and timbre) for deepfake detection. In this way, no semantic content will be exposed to the detector. To overcome the challenge of identifying diverse deepfake audio without semantic clues, we enhance our deepfake detector with real-world codec augmentation. Extensive experiments conducted on four benchmark datasets demonstrate SafeEar's effectiveness in detecting various deepfake techniques with an equal error rate (EER) down to 2.02%. Simultaneously, it shields five-language speech content from being deciphered by both machine and human auditory analysis, demonstrated by word error rates (WERs) all above 93.93% and our user study. Furthermore, our benchmark constructed for anti-deepfake and anti-content recovery evaluation helps provide a basis for future research in the realms of audio privacy preservation and deepfake detection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09272v1-abstract-full').style.display = 'none'; document.getElementById('2409.09272v1-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> 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">Accepted by ACM CCS 2024. Please cite this paper as "Xinfeng Li, Kai Li, Yifan Zheng, Chen Yan, Xiaoyu Ji, Wenyuan Xu. SafeEar: Content Privacy-Preserving Audio Deepfake Detection. In Proceedings of ACM Conference on Computer and Communications Security (CCS), 2024."</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.01696">arXiv:2408.01696</a> <span> [<a href="https://arxiv.org/pdf/2408.01696">pdf</a>, <a href="https://arxiv.org/format/2408.01696">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"> Generating High-quality Symbolic Music Using Fine-grained Discriminators </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zhedong Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+L">Liang Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jiehua Zhang</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Z">Zhenghui Hu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+H">Hongkui Wang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jian Yang</a>, <a href="/search/eess?searchtype=author&query=Qi%2C+Y">Yuankai Qi</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="2408.01696v1-abstract-short" style="display: inline;"> Existing symbolic music generation methods usually utilize discriminator to improve the quality of generated music via global perception of music. However, considering the complexity of information in music, such as rhythm and melody, a single discriminator cannot fully reflect the differences in these two primary dimensions of music. In this work, we propose to decouple the melody and rhythm from… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01696v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01696v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01696v1-abstract-full" style="display: none;"> Existing symbolic music generation methods usually utilize discriminator to improve the quality of generated music via global perception of music. However, considering the complexity of information in music, such as rhythm and melody, a single discriminator cannot fully reflect the differences in these two primary dimensions of music. In this work, we propose to decouple the melody and rhythm from music, and design corresponding fine-grained discriminators to tackle the aforementioned issues. Specifically, equipped with a pitch augmentation strategy, the melody discriminator discerns the melody variations presented by the generated samples. By contrast, the rhythm discriminator, enhanced with bar-level relative positional encoding, focuses on the velocity of generated notes. Such a design allows the generator to be more explicitly aware of which aspects should be adjusted in the generated music, making it easier to mimic human-composed music. Experimental results on the POP909 benchmark demonstrate the favorable performance of the proposed method compared to several state-of-the-art methods in terms of both objective and subjective metrics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01696v1-abstract-full').style.display = 'none'; document.getElementById('2408.01696v1-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 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">Accepted by ICPR2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.13357">arXiv:2406.13357</a> <span> [<a href="https://arxiv.org/pdf/2406.13357">pdf</a>, <a href="https://arxiv.org/format/2406.13357">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"> Transferable speech-to-text large language model alignment module </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wu%2C+B">Boyong Wu</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Pu%2C+H">Haoran Pu</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="2406.13357v1-abstract-short" style="display: inline;"> By leveraging the power of Large Language Models(LLMs) and speech foundation models, state of the art speech-text bimodal works can achieve challenging tasks like spoken translation(ST) and question answering(SQA) altogether with much simpler architectures. In this paper, we utilize the capability of Whisper encoder and pre-trained Yi-6B. Empirical results reveal that modal alignment can be achiev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13357v1-abstract-full').style.display = 'inline'; document.getElementById('2406.13357v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.13357v1-abstract-full" style="display: none;"> By leveraging the power of Large Language Models(LLMs) and speech foundation models, state of the art speech-text bimodal works can achieve challenging tasks like spoken translation(ST) and question answering(SQA) altogether with much simpler architectures. In this paper, we utilize the capability of Whisper encoder and pre-trained Yi-6B. Empirical results reveal that modal alignment can be achieved with one layer module and hundred hours of speech-text multitask corpus. We further swap the Yi-6B with human preferences aligned version of Yi-6B-Chat during inference, and discover that the alignment capability is applicable as well. In addition, the alignment subspace revealed by singular value decomposition(SVD) also implies linear alignment subspace is sparse, which leaves the possibility to concatenate other features like voice-print or video to expand modality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13357v1-abstract-full').style.display = 'none'; document.getElementById('2406.13357v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">Accepted by InterSpeech 2024; 5 pages, 2 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/2405.09582">arXiv:2405.09582</a> <span> [<a href="https://arxiv.org/pdf/2405.09582">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> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICECAI62591.2024.10675013">10.1109/ICECAI62591.2024.10675013 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> AD-Aligning: Emulating Human-like Generalization for Cognitive Domain Adaptation in Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zhuoying Li</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+B">Bohua Wan</a>, <a href="/search/eess?searchtype=author&query=Mu%2C+C">Cong Mu</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+R">Ruzhang Zhao</a>, <a href="/search/eess?searchtype=author&query=Qiu%2C+S">Shushan Qiu</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</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="2405.09582v2-abstract-short" style="display: inline;"> Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, a novel approach that combines adversarial training with source-target domain alignment to enhance generalization capabilities. By pretraining with Coral loss and standard loss, AD-Align… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09582v2-abstract-full').style.display = 'inline'; document.getElementById('2405.09582v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.09582v2-abstract-full" style="display: none;"> Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, a novel approach that combines adversarial training with source-target domain alignment to enhance generalization capabilities. By pretraining with Coral loss and standard loss, AD-Aligning aligns target domain statistics with those of the pretrained encoder, preserving robustness while accommodating domain shifts. Through extensive experiments on diverse datasets and domain shift scenarios, including noise-induced shifts and cognitive domain adaptation tasks, we demonstrate AD-Aligning's superior performance compared to existing methods such as Deep Coral and ADDA. Our findings highlight AD-Aligning's ability to emulate the nuanced cognitive processes inherent in human perception, making it a promising solution for real-world applications requiring adaptable and robust domain adaptation strategies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09582v2-abstract-full').style.display = 'none'; document.getElementById('2405.09582v2-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> 21 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">Accepted by 2024 5th International Conference on Electronic Communication and Artificial Intelligence</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.14441">arXiv:2404.14441</a> <span> [<a href="https://arxiv.org/pdf/2404.14441">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="Artificial Intelligence">cs.AI</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="Image and Video Processing">eess.IV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICETCI61221.2024.10594699">10.1109/ICETCI61221.2024.10594699 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Optimizing Contrail Detection: A Deep Learning Approach with EfficientNet-b4 Encoding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lin%2C+Q">Qunwei Lin</a>, <a href="/search/eess?searchtype=author&query=Leng%2C+Q">Qian Leng</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+Z">Zhicheng Ding</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+X">Xiaonan Xu</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="2404.14441v1-abstract-short" style="display: inline;"> In the pursuit of environmental sustainability, the aviation industry faces the challenge of minimizing its ecological footprint. Among the key solutions is contrail avoidance, targeting the linear ice-crystal clouds produced by aircraft exhaust. These contrails exacerbate global warming by trapping atmospheric heat, necessitating precise segmentation and comprehensive analysis of contrail images… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14441v1-abstract-full').style.display = 'inline'; document.getElementById('2404.14441v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.14441v1-abstract-full" style="display: none;"> In the pursuit of environmental sustainability, the aviation industry faces the challenge of minimizing its ecological footprint. Among the key solutions is contrail avoidance, targeting the linear ice-crystal clouds produced by aircraft exhaust. These contrails exacerbate global warming by trapping atmospheric heat, necessitating precise segmentation and comprehensive analysis of contrail images to gauge their environmental impact. However, this segmentation task is complex due to the varying appearances of contrails under different atmospheric conditions and potential misalignment issues in predictive modeling. This paper presents an innovative deep-learning approach utilizing the efficient net-b4 encoder for feature extraction, seamlessly integrating misalignment correction, soft labeling, and pseudo-labeling techniques to enhance the accuracy and efficiency of contrail detection in satellite imagery. The proposed methodology aims to redefine contrail image analysis and contribute to the objectives of sustainable aviation by providing a robust framework for precise contrail detection and analysis in satellite imagery, thus aiding in the mitigation of aviation's environmental impact. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14441v1-abstract-full').style.display = 'none'; document.getElementById('2404.14441v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.08549">arXiv:2404.08549</a> <span> [<a href="https://arxiv.org/pdf/2404.08549">pdf</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="Biological Physics">physics.bio-ph</span> </div> </div> <p class="title is-5 mathjax"> Practical Guidelines for Cell Segmentation Models Under Optical Aberrations in Microscopy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Peng%2C+B">Boyuan Peng</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jiaju Chen</a>, <a href="/search/eess?searchtype=author&query=Githinji%2C+P+B">P. Bilha Githinji</a>, <a href="/search/eess?searchtype=author&query=Gul%2C+I">Ijaz Gul</a>, <a href="/search/eess?searchtype=author&query=Ye%2C+Q">Qihui Ye</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+M">Minjiang Chen</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+P">Peiwu Qin</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+X">Xingru Huang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+D">Dongmei Yu</a>, <a href="/search/eess?searchtype=author&query=Ji%2C+J">Jiansong Ji</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhenglin 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="2404.08549v2-abstract-short" style="display: inline;"> Cell segmentation is essential in biomedical research for analyzing cellular morphology and behavior. Deep learning methods, particularly convolutional neural networks (CNNs), have revolutionized cell segmentation by extracting intricate features from images. However, the robustness of these methods under microscope optical aberrations remains a critical challenge. This study evaluates cell image… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08549v2-abstract-full').style.display = 'inline'; document.getElementById('2404.08549v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.08549v2-abstract-full" style="display: none;"> Cell segmentation is essential in biomedical research for analyzing cellular morphology and behavior. Deep learning methods, particularly convolutional neural networks (CNNs), have revolutionized cell segmentation by extracting intricate features from images. However, the robustness of these methods under microscope optical aberrations remains a critical challenge. This study evaluates cell image segmentation models under optical aberrations from fluorescence and bright field microscopy. By simulating different types of aberrations, including astigmatism, coma, spherical aberration, trefoil, and mixed aberrations, we conduct a thorough evaluation of various cell instance segmentation models using the DynamicNuclearNet (DNN) and LIVECell datasets, representing fluorescence and bright field microscopy cell datasets, respectively. We train and test several segmentation models, including the Otsu threshold method and Mask R-CNN with different network heads (FPN, C3) and backbones (ResNet, VGG, Swin Transformer), under aberrated conditions. Additionally, we provide usage recommendations for the Cellpose 2.0 Toolbox on complex cell degradation images. The results indicate that the combination of FPN and SwinS demonstrates superior robustness in handling simple cell images affected by minor aberrations. In contrast, Cellpose 2.0 proves effective for complex cell images under similar conditions. Furthermore, we innovatively propose the Point Spread Function Image Label Classification Model (PLCM). This model can quickly and accurately identify aberration types and amplitudes from PSF images, assisting researchers without optical training. Through PLCM, researchers can better apply our proposed cell segmentation guidelines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08549v2-abstract-full').style.display = 'none'; document.getElementById('2404.08549v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.08010">arXiv:2404.08010</a> <span> [<a href="https://arxiv.org/pdf/2404.08010">pdf</a>, <a href="https://arxiv.org/format/2404.08010">other</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="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Differentiable Search for Finding Optimal Quantization Strategy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+L">Lianqiang Li</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenqian Yan</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Yefei 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="2404.08010v2-abstract-short" style="display: inline;"> To accelerate and compress deep neural networks (DNNs), many network quantization algorithms have been proposed. Although the quantization strategy of any algorithm from the state-of-the-arts may outperform others in some network architectures, it is hard to prove the strategy is always better than others, and even cannot judge that the strategy is always the best choice for all layers in a networ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08010v2-abstract-full').style.display = 'inline'; document.getElementById('2404.08010v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.08010v2-abstract-full" style="display: none;"> To accelerate and compress deep neural networks (DNNs), many network quantization algorithms have been proposed. Although the quantization strategy of any algorithm from the state-of-the-arts may outperform others in some network architectures, it is hard to prove the strategy is always better than others, and even cannot judge that the strategy is always the best choice for all layers in a network. In other words, existing quantization algorithms are suboptimal as they ignore the different characteristics of different layers and quantize all layers by a uniform quantization strategy. To solve the issue, in this paper, we propose a differentiable quantization strategy search (DQSS) to assign optimal quantization strategy for individual layer by taking advantages of the benefits of different quantization algorithms. Specifically, we formulate DQSS as a differentiable neural architecture search problem and adopt an efficient convolution to efficiently explore the mixed quantization strategies from a global perspective by gradient-based optimization. We conduct DQSS for post-training quantization to enable their performance to be comparable with that in full precision models. We also employ DQSS in quantization-aware training for further validating the effectiveness of DQSS. To circumvent the expensive optimization cost when employing DQSS in quantization-aware training, we update the hyper-parameters and the network parameters in a single forward-backward pass. Besides, we adjust the optimization process to avoid the potential under-fitting problem. Comprehensive experiments on high level computer vision task, i.e., image classification, and low level computer vision task, i.e., image super-resolution, with various network architectures show that DQSS could outperform the state-of-the-arts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08010v2-abstract-full').style.display = 'none'; document.getElementById('2404.08010v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.11556">arXiv:2403.11556</a> <span> [<a href="https://arxiv.org/pdf/2403.11556">pdf</a>, <a href="https://arxiv.org/format/2403.11556">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"> Hierarchical Frequency-based Upsampling and Refining for Compressed Video Quality Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+Q">Qianyu Zhang</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+B">Bolun Zheng</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xinying Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Q">Quan Chen</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+Z">Zhunjie Zhu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Canjin Wang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zongpeng Li</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chengang Yan</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="2403.11556v1-abstract-short" style="display: inline;"> Video compression artifacts arise due to the quantization operation in the frequency domain. The goal of video quality enhancement is to reduce compression artifacts and reconstruct a visually-pleasant result. In this work, we propose a hierarchical frequency-based upsampling and refining neural network (HFUR) for compressed video quality enhancement. HFUR consists of two modules: implicit frequen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11556v1-abstract-full').style.display = 'inline'; document.getElementById('2403.11556v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.11556v1-abstract-full" style="display: none;"> Video compression artifacts arise due to the quantization operation in the frequency domain. The goal of video quality enhancement is to reduce compression artifacts and reconstruct a visually-pleasant result. In this work, we propose a hierarchical frequency-based upsampling and refining neural network (HFUR) for compressed video quality enhancement. HFUR consists of two modules: implicit frequency upsampling module (ImpFreqUp) and hierarchical and iterative refinement module (HIR). ImpFreqUp exploits DCT-domain prior derived through implicit DCT transform, and accurately reconstructs the DCT-domain loss via a coarse-to-fine transfer. Consequently, HIR is introduced to facilitate cross-collaboration and information compensation between the scales, thus further refine the feature maps and promote the visual quality of the final output. We demonstrate the effectiveness of the proposed modules via ablation experiments and visualized results. Extensive experiments on public benchmarks show that HFUR achieves state-of-the-art performance for both constant bit rate and constant QP modes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.11556v1-abstract-full').style.display = 'none'; document.getElementById('2403.11556v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.02307">arXiv:2403.02307</a> <span> [<a href="https://arxiv.org/pdf/2403.02307">pdf</a>, <a href="https://arxiv.org/format/2403.02307">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"> Harnessing Intra-group Variations Via a Population-Level Context for Pathology Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Githinji%2C+P+B">P. Bilha Githinji</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+X">Xi Yuan</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhenglin Chen</a>, <a href="/search/eess?searchtype=author&query=Gul%2C+I">Ijaz Gul</a>, <a href="/search/eess?searchtype=author&query=Shang%2C+D">Dingqi Shang</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+W">Wen Liang</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+J">Jianming Deng</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+D">Dan Zeng</a>, <a href="/search/eess?searchtype=author&query=yu%2C+D">Dongmei yu</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+P">Peiwu Qin</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="2403.02307v2-abstract-short" style="display: inline;"> Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished performance on texture-based medical images. This study introduces the notion of a population-level context for pathology detection and employs a graph th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02307v2-abstract-full').style.display = 'inline'; document.getElementById('2403.02307v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.02307v2-abstract-full" style="display: none;"> Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished performance on texture-based medical images. This study introduces the notion of a population-level context for pathology detection and employs a graph theoretic approach to model and incorporate it into the latent code of an autoencoder via a refinement module we term PopuSense. PopuSense seeks to capture additional intra-group variations inherent in biomedical data that a local or global context of the convolutional model might miss or smooth out. Proof-of-concept experiments on contrast-based and texture-based images, with minimal adaptation, encounter the existing preference for intensity-based input. Nevertheless, PopuSense demonstrates improved separability in contrast-based images, presenting an additional avenue for refining representations learned by a model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.02307v2-abstract-full').style.display = 'none'; document.getElementById('2403.02307v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.09467">arXiv:2310.09467</a> <span> [<a href="https://arxiv.org/pdf/2310.09467">pdf</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> </div> </div> <p class="title is-5 mathjax"> PC-bzip2: a phase-space continuity enhanced lossless compression algorithm for light field microscopy data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Su%2C+C">Changqing Su</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+Z">Zihan Lin</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+Y">You Zhou</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shuai Wang</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yuhan Gao</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+B">Bo Xiong</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="2310.09467v1-abstract-short" style="display: inline;"> Light-field fluorescence microscopy (LFM) is a powerful elegant compact method for long-term high-speed imaging of complex biological systems, such as neuron activities and rapid movements of organelles. LFM experiments typically generate terabytes image data and require a huge number of storage space. Some lossy compression algorithms have been proposed recently with good compression performance.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09467v1-abstract-full').style.display = 'inline'; document.getElementById('2310.09467v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.09467v1-abstract-full" style="display: none;"> Light-field fluorescence microscopy (LFM) is a powerful elegant compact method for long-term high-speed imaging of complex biological systems, such as neuron activities and rapid movements of organelles. LFM experiments typically generate terabytes image data and require a huge number of storage space. Some lossy compression algorithms have been proposed recently with good compression performance. However, since the specimen usually only tolerates low power density illumination for long-term imaging with low phototoxicity, the image signal-to-noise ratio (SNR) is relative-ly low, which will cause the loss of some efficient position or intensity information by using such lossy compression al-gorithms. Here, we propose a phase-space continuity enhanced bzip2 (PC-bzip2) lossless compression method for LFM data as a high efficiency and open-source tool, which combines GPU-based fast entropy judgement and multi-core-CPU-based high-speed lossless compression. Our proposed method achieves almost 10% compression ratio improvement while keeping the capability of high-speed compression, compared with original bzip2. We evaluated our method on fluorescence beads data and fluorescence staining cells data with different SNRs. Moreover, by introducing the temporal continuity, our method shows the superior compression ratio on time series data of zebrafish blood vessels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.09467v1-abstract-full').style.display = 'none'; document.getElementById('2310.09467v1-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> 13 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.02020">arXiv:2309.02020</a> <span> [<a href="https://arxiv.org/pdf/2309.02020">pdf</a>, <a href="https://arxiv.org/format/2309.02020">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"> RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+Y">Yunhao Zou</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Fu%2C+Y">Ying Fu</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="2309.02020v1-abstract-short" style="display: inline;"> High dynamic range (HDR) images capture much more intensity levels than standard ones. Current methods predominantly generate HDR images from 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing pipeline. However, it becomes a formidable task to retrieve extremely high dynamic range scenes from such limited bit-depth data. Unlike existing methods, the core ide… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02020v1-abstract-full').style.display = 'inline'; document.getElementById('2309.02020v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.02020v1-abstract-full" style="display: none;"> High dynamic range (HDR) images capture much more intensity levels than standard ones. Current methods predominantly generate HDR images from 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing pipeline. However, it becomes a formidable task to retrieve extremely high dynamic range scenes from such limited bit-depth data. Unlike existing methods, the core idea of this work is to incorporate more informative Raw sensor data to generate HDR images, aiming to recover scene information in hard regions (the darkest and brightest areas of an HDR scene). To this end, we propose a model tailor-made for Raw images, harnessing the unique features of Raw data to facilitate the Raw-to-HDR mapping. Specifically, we learn exposure masks to separate the hard and easy regions of a high dynamic scene. Then, we introduce two important guidances, dual intensity guidance, which guides less informative channels with more informative ones, and global spatial guidance, which extrapolates scene specifics over an extended spatial domain. To verify our Raw-to-HDR approach, we collect a large Raw/HDR paired dataset for both training and testing. Our empirical evaluations validate the superiority of the proposed Raw-to-HDR reconstruction model, as well as our newly captured dataset in the experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.02020v1-abstract-full').style.display = 'none'; document.getElementById('2309.02020v1-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 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </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">ICCV 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.01040">arXiv:2308.01040</a> <span> [<a href="https://arxiv.org/pdf/2308.01040">pdf</a>, <a href="https://arxiv.org/format/2308.01040">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</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"> Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+X">Xinfeng Li</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chen Yan</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+X">Xuancun Lu</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+Z">Zihan Zeng</a>, <a href="/search/eess?searchtype=author&query=Ji%2C+X">Xiaoyu Ji</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+W">Wenyuan Xu</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="2308.01040v3-abstract-short" style="display: inline;"> Automatic speech recognition (ASR) systems have been shown to be vulnerable to adversarial examples (AEs). Recent success all assumes that users will not notice or disrupt the attack process despite the existence of music/noise-like sounds and spontaneous responses from voice assistants. Nonetheless, in practical user-present scenarios, user awareness may nullify existing attack attempts that laun… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.01040v3-abstract-full').style.display = 'inline'; document.getElementById('2308.01040v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.01040v3-abstract-full" style="display: none;"> Automatic speech recognition (ASR) systems have been shown to be vulnerable to adversarial examples (AEs). Recent success all assumes that users will not notice or disrupt the attack process despite the existence of music/noise-like sounds and spontaneous responses from voice assistants. Nonetheless, in practical user-present scenarios, user awareness may nullify existing attack attempts that launch unexpected sounds or ASR usage. In this paper, we seek to bridge the gap in existing research and extend the attack to user-present scenarios. We propose VRIFLE, an inaudible adversarial perturbation (IAP) attack via ultrasound delivery that can manipulate ASRs as a user speaks. The inherent differences between audible sounds and ultrasounds make IAP delivery face unprecedented challenges such as distortion, noise, and instability. In this regard, we design a novel ultrasonic transformation model to enhance the crafted perturbation to be physically effective and even survive long-distance delivery. We further enable VRIFLE's robustness by adopting a series of augmentation on user and real-world variations during the generation process. In this way, VRIFLE features an effective real-time manipulation of the ASR output from different distances and under any speech of users, with an alter-and-mute strategy that suppresses the impact of user disruption. Our extensive experiments in both digital and physical worlds verify VRIFLE's effectiveness under various configurations, robustness against six kinds of defenses, and universality in a targeted manner. We also show that VRIFLE can be delivered with a portable attack device and even everyday-life loudspeakers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.01040v3-abstract-full').style.display = 'none'; document.getElementById('2308.01040v3-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> 12 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </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 NDSS Symposium 2024. Please cite this paper as "Xinfeng Li, Chen Yan, Xuancun Lu, Zihan Zeng, Xiaoyu Ji, Wenyuan Xu. Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time. In Network and Distributed System Security (NDSS) Symposium 2024."</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.14442">arXiv:2307.14442</a> <span> [<a href="https://arxiv.org/pdf/2307.14442">pdf</a>, <a href="https://arxiv.org/format/2307.14442">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</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="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Neural Schr枚dinger Bridge with Sinkhorn Losses: Application to Data-driven Minimum Effort Control of Colloidal Self-assembly </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Nodozi%2C+I">Iman Nodozi</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Charlie Yan</a>, <a href="/search/eess?searchtype=author&query=Khare%2C+M">Mira Khare</a>, <a href="/search/eess?searchtype=author&query=Halder%2C+A">Abhishek Halder</a>, <a href="/search/eess?searchtype=author&query=Mesbah%2C+A">Ali Mesbah</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="2307.14442v2-abstract-short" style="display: inline;"> We show that the minimum effort control of colloidal self-assembly can be naturally formulated in the order-parameter space as a generalized Schr枚dinger bridge problem -- a class of fixed-horizon stochastic optimal control problems that originated in the works of Erwin Schr枚dinger in the early 1930s. In recent years, this class of problems has seen a resurgence of research activities in the contro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.14442v2-abstract-full').style.display = 'inline'; document.getElementById('2307.14442v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.14442v2-abstract-full" style="display: none;"> We show that the minimum effort control of colloidal self-assembly can be naturally formulated in the order-parameter space as a generalized Schr枚dinger bridge problem -- a class of fixed-horizon stochastic optimal control problems that originated in the works of Erwin Schr枚dinger in the early 1930s. In recent years, this class of problems has seen a resurgence of research activities in the control and machine learning communities. Different from the existing literature on the theory and computation for such problems, the controlled drift and diffusion coefficients for colloidal self-assembly are typically nonaffine in control, and are difficult to obtain from physics-based modeling. We deduce the conditions of optimality for such generalized problems, and show that the resulting system of equations is structurally very different from the existing results in a way that standard computational approaches no longer apply. Thus motivated, we propose a data-driven learning and control framework, named `neural Schr枚dinger bridge', to solve such generalized Schr枚dinger bridge problems by innovating on recent advances in neural networks. We illustrate the effectiveness of the proposed framework using a numerical case study of colloidal self-assembly. We learn the controlled drift and diffusion coefficients as two neural networks using molecular dynamics simulation data, and then use these two to train a third network with Sinkhorn losses designed for distributional endpoint constraints, specific for this class of control problems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.14442v2-abstract-full').style.display = 'none'; document.getElementById('2307.14442v2-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> 13 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.17203">arXiv:2306.17203</a> <span> [<a href="https://arxiv.org/pdf/2306.17203">pdf</a>, <a href="https://arxiv.org/format/2306.17203">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="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="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Luo%2C+S">Simian Luo</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chuanhao Yan</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+C">Chenxu Hu</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+H">Hang Zhao</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="2306.17203v1-abstract-short" style="display: inline;"> The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.17203v1-abstract-full').style.display = 'inline'; document.getElementById('2306.17203v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.17203v1-abstract-full" style="display: none;"> The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semantically aligned features, then train an LDM with CAVP-aligned visual features on spectrogram latent space. The CAVP-aligned features enable LDM to capture the subtler audio-visual correlation via a cross-attention module. We further significantly improve sample quality with `double guidance'. Diff-Foley achieves state-of-the-art V2A performance on current large scale V2A dataset. Furthermore, we demonstrate Diff-Foley practical applicability and generalization capabilities via downstream finetuning. Project Page: see https://diff-foley.github.io/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.17203v1-abstract-full').style.display = 'none'; document.getElementById('2306.17203v1-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.16022">arXiv:2306.16022</a> <span> [<a href="https://arxiv.org/pdf/2306.16022">pdf</a>, <a href="https://arxiv.org/format/2306.16022">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="Cryptography and Security">cs.CR</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"> Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+X">Xinfeng Li</a>, <a href="/search/eess?searchtype=author&query=Ze%2C+J">Junning Ze</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chen Yan</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+Y">Yushi Cheng</a>, <a href="/search/eess?searchtype=author&query=Ji%2C+X">Xiaoyu Ji</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+W">Wenyuan Xu</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="2306.16022v2-abstract-short" style="display: inline;"> Automatic Speaker Recognition Systems (SRSs) have been widely used in voice applications for personal identification and access control. A typical SRS consists of three stages, i.e., training, enrollment, and recognition. Previous work has revealed that SRSs can be bypassed by backdoor attacks at the training stage or by adversarial example attacks at the recognition stage. In this paper, we propo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.16022v2-abstract-full').style.display = 'inline'; document.getElementById('2306.16022v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.16022v2-abstract-full" style="display: none;"> Automatic Speaker Recognition Systems (SRSs) have been widely used in voice applications for personal identification and access control. A typical SRS consists of three stages, i.e., training, enrollment, and recognition. Previous work has revealed that SRSs can be bypassed by backdoor attacks at the training stage or by adversarial example attacks at the recognition stage. In this paper, we propose Tuner, a new type of backdoor attack against the enrollment stage of SRS via adversarial ultrasound modulation, which is inaudible, synchronization-free, content-independent, and black-box. Our key idea is to first inject the backdoor into the SRS with modulated ultrasound when a legitimate user initiates the enrollment, and afterward, the polluted SRS will grant access to both the legitimate user and the adversary with high confidence. Our attack faces a major challenge of unpredictable user articulation at the enrollment stage. To overcome this challenge, we generate the ultrasonic backdoor by augmenting the optimization process with random speech content, vocalizing time, and volume of the user. Furthermore, to achieve real-world robustness, we improve the ultrasonic signal over traditional methods using sparse frequency points, pre-compensation, and single-sideband (SSB) modulation. We extensively evaluate Tuner on two common datasets and seven representative SRS models, as well as its robustness against seven kinds of defenses. Results show that our attack can successfully bypass speaker recognition systems while remaining effective to various speakers, speech content, etc. To mitigate this newly discovered threat, we also provide discussions on potential countermeasures, limitations, and future works of this new threat. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.16022v2-abstract-full').style.display = 'none'; document.getElementById('2306.16022v2-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </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">Published in Internet of Things Journal (IoT-J)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.00595">arXiv:2304.00595</a> <span> [<a href="https://arxiv.org/pdf/2304.00595">pdf</a>, <a href="https://arxiv.org/format/2304.00595">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</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="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Mathematical Physics">math-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Dynamical Systems">math.DS</span> </div> </div> <p class="title is-5 mathjax"> Optimal Mass Transport over the Euler Equation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Charlie Yan</a>, <a href="/search/eess?searchtype=author&query=Nodozi%2C+I">Iman Nodozi</a>, <a href="/search/eess?searchtype=author&query=Halder%2C+A">Abhishek Halder</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="2304.00595v1-abstract-short" style="display: inline;"> We consider the finite horizon optimal steering of the joint state probability distribution subject to the angular velocity dynamics governed by the Euler equation. The problem and its solution amounts to controlling the spin of a rigid body via feedback, and is of practical importance, for example, in angular stabilization of a spacecraft with stochastic initial and terminal states. We clarify ho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.00595v1-abstract-full').style.display = 'inline'; document.getElementById('2304.00595v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.00595v1-abstract-full" style="display: none;"> We consider the finite horizon optimal steering of the joint state probability distribution subject to the angular velocity dynamics governed by the Euler equation. The problem and its solution amounts to controlling the spin of a rigid body via feedback, and is of practical importance, for example, in angular stabilization of a spacecraft with stochastic initial and terminal states. We clarify how this problem is an instance of the optimal mass transport (OMT) problem with bilinear prior drift. We deduce both static and dynamic versions of the Eulerian OMT, and provide analytical and numerical results for the synthesis of the optimal controller. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.00595v1-abstract-full').style.display = 'none'; document.getElementById('2304.00595v1-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 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.17706">arXiv:2303.17706</a> <span> [<a href="https://arxiv.org/pdf/2303.17706">pdf</a>, <a href="https://arxiv.org/format/2303.17706">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="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> Label Propagation via Random Walk for Training Robust Thalamus Nuclei Parcellation Model from Noisy Annotations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Feng%2C+A">Anqi Feng</a>, <a href="/search/eess?searchtype=author&query=Xue%2C+Y">Yuan Xue</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yuli Wang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chang Yan</a>, <a href="/search/eess?searchtype=author&query=Bian%2C+Z">Zhangxing Bian</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+M">Muhan Shao</a>, <a href="/search/eess?searchtype=author&query=Zhuo%2C+J">Jiachen Zhuo</a>, <a href="/search/eess?searchtype=author&query=Gullapalli%2C+R+P">Rao P. Gullapalli</a>, <a href="/search/eess?searchtype=author&query=Carass%2C+A">Aaron Carass</a>, <a href="/search/eess?searchtype=author&query=Prince%2C+J+L">Jerry L. Prince</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="2303.17706v1-abstract-short" style="display: inline;"> Data-driven thalamic nuclei parcellation depends on high-quality manual annotations. However, the small size and low contrast changes among thalamic nuclei, yield annotations that are often incomplete, noisy, or ambiguously labelled. To train a robust thalamic nuclei parcellation model with noisy annotations, we propose a label propagation algorithm based on random walker to refine the annotations… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.17706v1-abstract-full').style.display = 'inline'; document.getElementById('2303.17706v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.17706v1-abstract-full" style="display: none;"> Data-driven thalamic nuclei parcellation depends on high-quality manual annotations. However, the small size and low contrast changes among thalamic nuclei, yield annotations that are often incomplete, noisy, or ambiguously labelled. To train a robust thalamic nuclei parcellation model with noisy annotations, we propose a label propagation algorithm based on random walker to refine the annotations before model training. A two-step model was trained to generate first the whole thalamus and then the nuclei masks. We conducted experiments on a mild traumatic brain injury~(mTBI) dataset with noisy thalamic nuclei annotations. Our model outperforms current state-of-the-art thalamic nuclei parcellations by a clear margin. We believe our method can also facilitate the training of other parcellation models with noisy labels. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.17706v1-abstract-full').style.display = 'none'; document.getElementById('2303.17706v1-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.09040">arXiv:2303.09040</a> <span> [<a href="https://arxiv.org/pdf/2303.09040">pdf</a>, <a href="https://arxiv.org/format/2303.09040">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"> Hybrid Spectral Denoising Transformer with Guided Attention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lai%2C+Z">Zeqiang Lai</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Fu%2C+Y">Ying Fu</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="2303.09040v2-abstract-short" style="display: inline;"> In this paper, we present a Hybrid Spectral Denoising Transformer (HSDT) for hyperspectral image denoising. Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the global and local spatial-spectral correlations while maintaining efficiency and flexibility. To address these issues, we introduce a hybrid approach tha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.09040v2-abstract-full').style.display = 'inline'; document.getElementById('2303.09040v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.09040v2-abstract-full" style="display: none;"> In this paper, we present a Hybrid Spectral Denoising Transformer (HSDT) for hyperspectral image denoising. Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the global and local spatial-spectral correlations while maintaining efficiency and flexibility. To address these issues, we introduce a hybrid approach that combines the advantages of both models with a Spatial-Spectral Separable Convolution (S3Conv), Guided Spectral Self-Attention (GSSA), and Self-Modulated Feed-Forward Network (SM-FFN). Our S3Conv works as a lightweight alternative to 3D convolution, which extracts more spatial-spectral correlated features while keeping the flexibility to tackle HSIs with an arbitrary number of bands. These features are then adaptively processed by GSSA which per-forms 3D self-attention across the spectral bands, guided by a set of learnable queries that encode the spectral signatures. This not only enriches our model with powerful capabilities for identifying global spectral correlations but also maintains linear complexity. Moreover, our SM-FFN proposes the self-modulation that intensifies the activations of more informative regions, which further strengthens the aggregated features. Extensive experiments are conducted on various datasets under both simulated and real-world noise, and it shows that our HSDT significantly outperforms the existing state-of-the-art methods while maintaining low computational overhead. Code is at https: //github.com/Zeqiang-Lai/HSDT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.09040v2-abstract-full').style.display = 'none'; document.getElementById('2303.09040v2-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> 8 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </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">ICCV 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.06114">arXiv:2301.06114</a> <span> [<a href="https://arxiv.org/pdf/2301.06114">pdf</a>, <a href="https://arxiv.org/format/2301.06114">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"> Segmenting thalamic nuclei from manifold projections of multi-contrast MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chang Yan</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+M">Muhan Shao</a>, <a href="/search/eess?searchtype=author&query=Bian%2C+Z">Zhangxing Bian</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+A">Anqi Feng</a>, <a href="/search/eess?searchtype=author&query=Xue%2C+Y">Yuan Xue</a>, <a href="/search/eess?searchtype=author&query=Zhuo%2C+J">Jiachen Zhuo</a>, <a href="/search/eess?searchtype=author&query=Gullapalli%2C+R+P">Rao P. Gullapalli</a>, <a href="/search/eess?searchtype=author&query=Carass%2C+A">Aaron Carass</a>, <a href="/search/eess?searchtype=author&query=Prince%2C+J+L">Jerry L. Prince</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="2301.06114v3-abstract-short" style="display: inline;"> The thalamus is a subcortical gray matter structure that plays a key role in relaying sensory and motor signals within the brain. Its nuclei can atrophy or otherwise be affected by neurological disease and injuries including mild traumatic brain injury. Segmenting both the thalamus and its nuclei is challenging because of the relatively low contrast within and around the thalamus in conventional m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06114v3-abstract-full').style.display = 'inline'; document.getElementById('2301.06114v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.06114v3-abstract-full" style="display: none;"> The thalamus is a subcortical gray matter structure that plays a key role in relaying sensory and motor signals within the brain. Its nuclei can atrophy or otherwise be affected by neurological disease and injuries including mild traumatic brain injury. Segmenting both the thalamus and its nuclei is challenging because of the relatively low contrast within and around the thalamus in conventional magnetic resonance (MR) images. This paper explores imaging features to determine key tissue signatures that naturally cluster, from which we can parcellate thalamic nuclei. Tissue contrasts include T1-weighted and T2-weighted images, MR diffusion measurements including FA, mean diffusivity, Knutsson coefficients that represent fiber orientation, and synthetic multi-TI images derived from FGATIR and T1-weighted images. After registration of these contrasts and isolation of the thalamus, we use the uniform manifold approximation and projection (UMAP) method for dimensionality reduction to produce a low-dimensional representation of the data within the thalamus. Manual labeling of the thalamus provides labels for our UMAP embedding from which k nearest neighbors can be used to label new unseen voxels in that same UMAP embedding. N -fold cross-validation of the method reveals comparable performance to state-of-the-art methods for thalamic parcellation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06114v3-abstract-full').style.display = 'none'; document.getElementById('2301.06114v3-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> 31 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </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, 3 figures, 2023 SPIE-MI Image Processing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.05256">arXiv:2211.05256</a> <span> [<a href="https://arxiv.org/pdf/2211.05256">pdf</a>, <a href="https://arxiv.org/format/2211.05256">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"> Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ignatov%2C+A">Andrey Ignatov</a>, <a href="/search/eess?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/eess?searchtype=author&query=Chiang%2C+C">Cheng-Ming Chiang</a>, <a href="/search/eess?searchtype=author&query=Kuo%2C+H">Hsien-Kai Kuo</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yu-Syuan Xu</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+M">Man-Yu Lee</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+A">Allen Lu</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+C">Chia-Ming Cheng</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+C">Chih-Cheng Chen</a>, <a href="/search/eess?searchtype=author&query=Yong%2C+J">Jia-Ying Yong</a>, <a href="/search/eess?searchtype=author&query=Shuai%2C+H">Hong-Han Shuai</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+W">Wen-Huang Cheng</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+Z">Zhuang Jia</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+T">Tianyu Xu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yijian Zhang</a>, <a href="/search/eess?searchtype=author&query=Bao%2C+L">Long Bao</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+H">Heng Sun</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+D">Diankai Zhang</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+S">Si Gao</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shaoli Liu</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+B">Biao Wu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xiaofeng Zhang</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+C">Chengjian Zheng</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+K">Kaidi Lu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+N">Ning Wang</a> , et al. (29 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="2211.05256v1-abstract-short" style="display: inline;"> Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this prob… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.05256v1-abstract-full').style.display = 'inline'; document.getElementById('2211.05256v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.05256v1-abstract-full" style="display: none;"> Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.05256v1-abstract-full').style.display = 'none'; document.getElementById('2211.05256v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </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">arXiv admin note: text overlap with arXiv:2105.08826, arXiv:2105.07809, arXiv:2211.04470, arXiv:2211.03885</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2209.13300">arXiv:2209.13300</a> <span> [<a href="https://arxiv.org/pdf/2209.13300">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="Optics">physics.optics</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.3788/COL202321.061103">10.3788/COL202321.061103 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Passive Non-line-of-sight Imaging for Moving Targets with an Event Camera </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+C">Conghe Wang</a>, <a href="/search/eess?searchtype=author&query=He%2C+Y">Yutong He</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xia Wang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+H">Honghao Huang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Changda Yan</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xin Zhang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+H">Hongwei 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="2209.13300v1-abstract-short" style="display: inline;"> Non-line-of-sight (NLOS) imaging is an emerging technique for detecting objects behind obstacles or around corners. Recent studies on passive NLOS mainly focus on steady-state measurement and reconstruction methods, which show limitations in recognition of moving targets. To the best of our knowledge, we propose a novel event-based passive NLOS imaging method. We acquire asynchronous event-based d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.13300v1-abstract-full').style.display = 'inline'; document.getElementById('2209.13300v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.13300v1-abstract-full" style="display: none;"> Non-line-of-sight (NLOS) imaging is an emerging technique for detecting objects behind obstacles or around corners. Recent studies on passive NLOS mainly focus on steady-state measurement and reconstruction methods, which show limitations in recognition of moving targets. To the best of our knowledge, we propose a novel event-based passive NLOS imaging method. We acquire asynchronous event-based data which contains detailed dynamic information of the NLOS target, and efficiently ease the degradation of speckle caused by movement. Besides, we create the first event-based NLOS imaging dataset, NLOS-ES, and the event-based feature is extracted by time-surface representation. We compare the reconstructions through event-based data with frame-based data. The event-based method performs well on PSNR and LPIPS, which is 20% and 10% better than frame-based method, while the data volume takes only 2% of traditional method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.13300v1-abstract-full').style.display = 'none'; document.getElementById('2209.13300v1-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> [J]. Chinese Optics Letters, 2023, 21(6): 061103 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.05284">arXiv:2207.05284</a> <span> [<a href="https://arxiv.org/pdf/2207.05284">pdf</a>, <a href="https://arxiv.org/format/2207.05284">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"> High-Order Leader-Follower Tracking Control under Limited Information Availability </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chuan Yan</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+T">Tao Yang</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+H">Huazhen Fang</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="2207.05284v1-abstract-short" style="display: inline;"> Limited information availability represents a fundamental challenge for control of multi-agent systems, since an agent often lacks sensing capabilities to measure certain states of its own and can exchange data only with its neighbors. The challenge becomes even greater when agents are governed by high-order dynamics. The present work is motivated to conduct control design for linear and nonlinear… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.05284v1-abstract-full').style.display = 'inline'; document.getElementById('2207.05284v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.05284v1-abstract-full" style="display: none;"> Limited information availability represents a fundamental challenge for control of multi-agent systems, since an agent often lacks sensing capabilities to measure certain states of its own and can exchange data only with its neighbors. The challenge becomes even greater when agents are governed by high-order dynamics. The present work is motivated to conduct control design for linear and nonlinear high-order leader-follower multi-agent systems in a context where only the first state of an agent is measured. To address this open challenge, we develop novel distributed observers to enable followers to reconstruct unmeasured or unknown quantities about themselves and the leader and on such a basis, build observer-based tracking control approaches. We analyze the convergence properties of the proposed approaches and validate their performance through simulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.05284v1-abstract-full').style.display = 'none'; document.getElementById('2207.05284v1-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 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.04227">arXiv:2205.04227</a> <span> [<a href="https://arxiv.org/pdf/2205.04227">pdf</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"> Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yang Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+E">Ersi Zhang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+L">Lulu Xu</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+C">Chufan Xiao</a>, <a href="/search/eess?searchtype=author&query=Zhong%2C+X">Xiaoyun Zhong</a>, <a href="/search/eess?searchtype=author&query=Lian%2C+L">Lijin Lian</a>, <a href="/search/eess?searchtype=author&query=Li%2C+F">Fang Li</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+B">Bin Jiang</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+Y">Yuhan Dong</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+L">Lan Ma</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Q">Qiming Huang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+M">Ming Xu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yongbing Zhang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+D">Dongmei Yu</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+P">Peiwu Qin</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="2205.04227v1-abstract-short" style="display: inline;"> Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.04227v1-abstract-full').style.display = 'inline'; document.getElementById('2205.04227v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.04227v1-abstract-full" style="display: none;"> Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-consuming and labor-intensive, in contrast to image-level labels that are easier to obtain. It is imperative to resolve this problem through weakly-supervised semantic segmentation models using image-level labels as supervision since it can significantly reduce human annotation efforts. Most of the advanced solutions exploit class activation mapping (CAM). However, the original CAMs rarely capture the precise boundaries of lesions. In this study, we propose the strategy of multi-scale inference to refine CAMs by reducing the detail loss in single-scale reasoning. For segmentation, we develop a novel model named Mixed-UNet, which has two parallel branches in the decoding phase. The results can be obtained after fusing the extracted features from two branches. We evaluate the designed Mixed-UNet against several prevalent deep learning-based segmentation approaches on our dataset collected from the local hospital and public datasets. The validation results demonstrate that our model surpasses available methods under the same supervision level in the segmentation of various lesions from brain imaging. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.04227v1-abstract-full').style.display = 'none'; document.getElementById('2205.04227v1-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </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, 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/2111.04985">arXiv:2111.04985</a> <span> [<a href="https://arxiv.org/pdf/2111.04985">pdf</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"> Bilinear pooling and metric learning network for early Alzheimer's disease identification with FDG-PET images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Cui%2C+W">Wenju Cui</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Caiying Yan</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+Z">Zhuangzhi Yan</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+Y">Yunsong Peng</a>, <a href="/search/eess?searchtype=author&query=Leng%2C+Y">Yilin Leng</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+C">Chenlu Liu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+S">Shuangqing Chen</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+X">Xi 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="2111.04985v1-abstract-short" style="display: inline;"> FDG-PET reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. However, the studies of identification of early MCI (EMCI) and late MCI (LMCI) with FDG-PET images are stil… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.04985v1-abstract-full').style.display = 'inline'; document.getElementById('2111.04985v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.04985v1-abstract-full" style="display: none;"> FDG-PET reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. However, the studies of identification of early MCI (EMCI) and late MCI (LMCI) with FDG-PET images are still insufficient. Compared with studies based on fMRI and DTI images, the researches of the inter-region representation features in FDG-PET images are insufficient. Moreover, considering the variability in different individuals, some hard samples which are very similar with both two classes limit the classification performance. To tackle these problems, in this paper, we propose a novel bilinear pooling and metric learning network (BMNet), which can extract the inter-region representation features and distinguish hard samples by constructing embedding space. To validate the proposed method, we collect 998 FDG-PET images from ADNI. Following the common preprocessing steps, 90 features are extracted from each FDG-PET image according to the automatic anatomical landmark (AAL) template and then sent into the proposed network. Extensive 5-fold cross-validation experiments are performed for multiple two-class classifications. Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively. Specifically, in the classification task between EMCI and LMCI, the specificity improves 6.38% after adding the triple metric loss, and the negative predictive value (NPV) improves 3.45% after using the bilinear pooling module. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.04985v1-abstract-full').style.display = 'none'; document.getElementById('2111.04985v1-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> 9 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.00617">arXiv:2109.00617</a> <span> [<a href="https://arxiv.org/pdf/2109.00617">pdf</a>, <a href="https://arxiv.org/format/2109.00617">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> LinEasyBO: Scalable Bayesian Optimization Approach for Analog Circuit Synthesis via One-Dimensional Subspaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shuhan Zhang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Changhao Yan</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+D">Dian Zhou</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+X">Xuan Zeng</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="2109.00617v1-abstract-short" style="display: inline;"> A large body of literature has proved that the Bayesian optimization framework is especially efficient and effective in analog circuit synthesis. However, most of the previous research works only focus on designing informative surrogate models or efficient acquisition functions. Even if searching for the global optimum over the acquisition function surface is itself a difficult task, it has been l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.00617v1-abstract-full').style.display = 'inline'; document.getElementById('2109.00617v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.00617v1-abstract-full" style="display: none;"> A large body of literature has proved that the Bayesian optimization framework is especially efficient and effective in analog circuit synthesis. However, most of the previous research works only focus on designing informative surrogate models or efficient acquisition functions. Even if searching for the global optimum over the acquisition function surface is itself a difficult task, it has been largely ignored. In this paper, we propose a fast and robust Bayesian optimization approach via one-dimensional subspaces for analog circuit synthesis. By solely focusing on optimizing one-dimension subspaces at each iteration, we greatly reduce the computational overhead of the Bayesian optimization framework while safely maximizing the acquisition function. By combining the benefits of different dimension selection strategies, we adaptively balancing between searching globally and locally. By leveraging the batch Bayesian optimization framework, we further accelerate the optimization procedure by making full use of the hardware resources. Experimental results quantitatively show that our proposed algorithm can accelerate the optimization procedure by up to 9x and 38x compared to LP-EI and REMBOpBO respectively when the batch size is 15. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.00617v1-abstract-full').style.display = 'none'; document.getElementById('2109.00617v1-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> 1 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </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">6 pages, 4 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/2107.13353">arXiv:2107.13353</a> <span> [<a href="https://arxiv.org/pdf/2107.13353">pdf</a>, <a href="https://arxiv.org/format/2107.13353">other</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="Artificial Intelligence">cs.AI</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"> Fast Wireless Sensor Anomaly Detection based on Data Stream in Edge Computing Enabled Smart Greenhouse </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yang%2C+Y">Yihong Yang</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+S">Sheng Ding</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yuwen Liu</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+S">Shunmei Meng</a>, <a href="/search/eess?searchtype=author&query=Chi%2C+X">Xiaoxiao Chi</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+R">Rui Ma</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</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="2107.13353v1-abstract-short" style="display: inline;"> Edge computing enabled smart greenhouse is a representative application of Internet of Things technology, which can monitor the environmental information in real time and employ the information to contribute to intelligent decision-making. In the process, anomaly detection for wireless sensor data plays an important role. However, traditional anomaly detection algorithms originally designed for an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.13353v1-abstract-full').style.display = 'inline'; document.getElementById('2107.13353v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.13353v1-abstract-full" style="display: none;"> Edge computing enabled smart greenhouse is a representative application of Internet of Things technology, which can monitor the environmental information in real time and employ the information to contribute to intelligent decision-making. In the process, anomaly detection for wireless sensor data plays an important role. However, traditional anomaly detection algorithms originally designed for anomaly detection in static data have not properly considered the inherent characteristics of data stream produced by wireless sensor such as infiniteness, correlations and concept drift, which may pose a considerable challenge on anomaly detection based on data stream, and lead to low detection accuracy and efficiency. First, data stream usually generates quickly which means that it is infinite and enormous, so any traditional off-line anomaly detection algorithm that attempts to store the whole dataset or to scan the dataset multiple times for anomaly detection will run out of memory space. Second, there exist correlations among different data streams, which traditional algorithms hardly consider. Third, the underlying data generation process or data distribution may change over time. Thus, traditional anomaly detection algorithms with no model update will lose their effects. Considering these issues, a novel method (called DLSHiForest) on basis of Locality-Sensitive Hashing and time window technique in this paper is proposed to solve these problems while achieving accurate and efficient detection. Comprehensive experiments are executed using real-world agricultural greenhouse dataset to demonstrate the feasibility of our approach. Experimental results show that our proposal is practicable in addressing challenges of traditional anomaly detection while ensuring accuracy and efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.13353v1-abstract-full').style.display = 'none'; document.getElementById('2107.13353v1-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> 28 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </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, 8 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/2106.15412">arXiv:2106.15412</a> <span> [<a href="https://arxiv.org/pdf/2106.15412">pdf</a>, <a href="https://arxiv.org/format/2106.15412">other</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="Systems and Control">eess.SY</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TCAD.2021.3054811">10.1109/TCAD.2021.3054811 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An Efficient Batch Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multi-objective Acquisition Ensemble </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shuhan Zhang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Changhao Yan</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+D">Dian Zhou</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+X">Xuan Zeng</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="2106.15412v1-abstract-short" style="display: inline;"> Bayesian optimization is a promising methodology for analog circuit synthesis. However, the sequential nature of the Bayesian optimization framework significantly limits its ability to fully utilize real-world computational resources. In this paper, we propose an efficient parallelizable Bayesian optimization algorithm via Multi-objective ACquisition function Ensemble (MACE) to further accelerate… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.15412v1-abstract-full').style.display = 'inline'; document.getElementById('2106.15412v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.15412v1-abstract-full" style="display: none;"> Bayesian optimization is a promising methodology for analog circuit synthesis. However, the sequential nature of the Bayesian optimization framework significantly limits its ability to fully utilize real-world computational resources. In this paper, we propose an efficient parallelizable Bayesian optimization algorithm via Multi-objective ACquisition function Ensemble (MACE) to further accelerate the optimization procedure. By sampling query points from the Pareto front of the probability of improvement (PI), expected improvement (EI) and lower confidence bound (LCB), we combine the benefits of state-of-the-art acquisition functions to achieve a delicate tradeoff between exploration and exploitation for the unconstrained optimization problem. Based on this batch design, we further adjust the algorithm for the constrained optimization problem. By dividing the optimization procedure into two stages and first focusing on finding an initial feasible point, we manage to gain more information about the valid region and can better avoid sampling around the infeasible area. After achieving the first feasible point, we favor the feasible region by adopting a specially designed penalization term to the acquisition function ensemble. The experimental results quantitatively demonstrate that our proposed algorithm can reduce the overall simulation time by up to 74 times compared to differential evolution (DE) for the unconstrained optimization problem when the batch size is 15. For the constrained optimization problem, our proposed algorithm can speed up the optimization process by up to 15 times compared to the weighted expected improvement based Bayesian optimization (WEIBO) approach, when the batch size is 15. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.15412v1-abstract-full').style.display = 'none'; document.getElementById('2106.15412v1-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> 28 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </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">14 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/2104.05507">arXiv:2104.05507</a> <span> [<a href="https://arxiv.org/pdf/2104.05507">pdf</a>, <a href="https://arxiv.org/format/2104.05507">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 class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.21437/Interspeech.2021-739">10.21437/Interspeech.2021-739 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> BART based semantic correction for Mandarin automatic speech recognition system </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhao%2C+Y">Yun Zhao</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+X">Xuerui Yang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jinchao Wang</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yongyu Gao</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+Y">Yuanfu Zhou</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="2104.05507v1-abstract-short" style="display: inline;"> Although automatic speech recognition (ASR) systems achieved significantly improvements in recent years, spoken language recognition error occurs which can be easily spotted by human beings. Various language modeling techniques have been developed on post recognition tasks like semantic correction. In this paper, we propose a Transformer based semantic correction method with pretrained BART initia… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.05507v1-abstract-full').style.display = 'inline'; document.getElementById('2104.05507v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.05507v1-abstract-full" style="display: none;"> Although automatic speech recognition (ASR) systems achieved significantly improvements in recent years, spoken language recognition error occurs which can be easily spotted by human beings. Various language modeling techniques have been developed on post recognition tasks like semantic correction. In this paper, we propose a Transformer based semantic correction method with pretrained BART initialization, Experiments on 10000 hours Mandarin speech dataset show that character error rate (CER) can be effectively reduced by 21.7% relatively compared to our baseline ASR system. Expert evaluation demonstrates that actual improvement of our model surpasses what CER indicates. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.05507v1-abstract-full').style.display = 'none'; document.getElementById('2104.05507v1-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 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </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">submitted to INTERSPEECH2021</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Interspeech 2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.16424">arXiv:2103.16424</a> <span> [<a href="https://arxiv.org/pdf/2103.16424">pdf</a>, <a href="https://arxiv.org/format/2103.16424">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"> Two-stage Robust Energy Storage Planning with Probabilistic Guarantees: A Data-driven Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Geng%2C+X">Xinbo Geng</a>, <a href="/search/eess?searchtype=author&query=Bie%2C+Z">Zhaohong Bie</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+L">Le Xie</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="2103.16424v4-abstract-short" style="display: inline;"> This paper addresses a central challenge of jointly considering shorter-term (e.g. hourly) and longer-term (e.g. yearly) uncertainties in power system planning with increasing penetration of renewable and storage resources. In conventional planning decision making, shorter-term (e.g., hourly) variations are not explicitly accounted for. However, given the deepening penetration of variable resource… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.16424v4-abstract-full').style.display = 'inline'; document.getElementById('2103.16424v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.16424v4-abstract-full" style="display: none;"> This paper addresses a central challenge of jointly considering shorter-term (e.g. hourly) and longer-term (e.g. yearly) uncertainties in power system planning with increasing penetration of renewable and storage resources. In conventional planning decision making, shorter-term (e.g., hourly) variations are not explicitly accounted for. However, given the deepening penetration of variable resources, it is becoming imperative to consider such shorter-term variation in the longer-term planning exercise. By leveraging the abundant amount of operational observation data, we propose a scenario-based robust planning framework that provides rigorous guarantees on the future operation risk of planning decisions considering a broad range of operational conditions, such as renewable generation fluctuations and load variations. By connecting two-stage robust optimization with the scenario approach theory, we show that with a carefully chosen number of scenarios, the operational risk level of the robust solution can be adaptive to the risk preference set by planners. The theoretical guarantees hold true for any distributions, and the proposed approach is scalable towards real-world power grids. Furthermore, the column-and-constraint generation algorithm is used to solve the two-stage robust planning problem and tighten theoretical guarantees. We substantiate this framework through a planning problem of energy storage in a power grid with deep renewable penetration. Case studies are performed on large-scale test systems (modified IEEE 118-bus system) to illustrate the theoretical bounds as well as the scalability of proposed algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.16424v4-abstract-full').style.display = 'none'; document.getElementById('2103.16424v4-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.08074">arXiv:2101.08074</a> <span> [<a href="https://arxiv.org/pdf/2101.08074">pdf</a>, <a href="https://arxiv.org/format/2101.08074">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="Artificial Intelligence">cs.AI</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="Multiagent Systems">cs.MA</span> </div> </div> <p class="title is-5 mathjax"> Flocking and Collision Avoidance for a Dynamic Squad of Fixed-Wing UAVs Using Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Xiang%2C+X">Xiaojia Xiang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Chang Wang</a>, <a href="/search/eess?searchtype=author&query=Lan%2C+Z">Zhen Lan</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="2101.08074v2-abstract-short" style="display: inline;"> Developing the flocking behavior for a dynamic squad of fixed-wing UAVs is still a challenge due to kinematic complexity and environmental uncertainty. In this paper, we deal with the decentralized flocking and collision avoidance problem through deep reinforcement learning (DRL). Specifically, we formulate a decentralized DRL-based decision making framework from the perspective of every follower,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.08074v2-abstract-full').style.display = 'inline'; document.getElementById('2101.08074v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.08074v2-abstract-full" style="display: none;"> Developing the flocking behavior for a dynamic squad of fixed-wing UAVs is still a challenge due to kinematic complexity and environmental uncertainty. In this paper, we deal with the decentralized flocking and collision avoidance problem through deep reinforcement learning (DRL). Specifically, we formulate a decentralized DRL-based decision making framework from the perspective of every follower, where a collision avoidance mechanism is integrated into the flocking controller. Then, we propose a novel reinforcement learning algorithm PS-CACER for training a shared control policy for all the followers. Besides, we design a plug-n-play embedding module based on convolutional neural networks and the attention mechanism. As a result, the variable-length system state can be encoded into a fixed-length embedding vector, which makes the learned DRL policy independent with the number and the order of followers. Finally, numerical simulation results demonstrate the effectiveness of the proposed method, and the learned policies can be directly transferred to semi-physical simulation without any parameter finetuning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.08074v2-abstract-full').style.display = 'none'; document.getElementById('2101.08074v2-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 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </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 for publication in the proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2101.05442">arXiv:2101.05442</a> <span> [<a href="https://arxiv.org/pdf/2101.05442">pdf</a>, <a href="https://arxiv.org/format/2101.05442">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=He%2C+X">Xin He</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shihao Wang</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+X">Xiaowen Chu</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+S">Shaohuai Shi</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+J">Jiangping Tang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+X">Xin Liu</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jiyong Zhang</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+G">Guiguang Ding</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="2101.05442v2-abstract-short" style="display: inline;"> The COVID-19 pandemic has spread globally for several months. Because its transmissibility and high pathogenicity seriously threaten people's lives, it is crucial to accurately and quickly detect COVID-19 infection. Many recent studies have shown that deep learning (DL) based solutions can help detect COVID-19 based on chest CT scans. However, most existing work focuses on 2D datasets, which may r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.05442v2-abstract-full').style.display = 'inline'; document.getElementById('2101.05442v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.05442v2-abstract-full" style="display: none;"> The COVID-19 pandemic has spread globally for several months. Because its transmissibility and high pathogenicity seriously threaten people's lives, it is crucial to accurately and quickly detect COVID-19 infection. Many recent studies have shown that deep learning (DL) based solutions can help detect COVID-19 based on chest CT scans. However, most existing work focuses on 2D datasets, which may result in low quality models as the real CT scans are 3D images. Besides, the reported results span a broad spectrum on different datasets with a relatively unfair comparison. In this paper, we first use three state-of-the-art 3D models (ResNet3D101, DenseNet3D121, and MC3\_18) to establish the baseline performance on the three publicly available chest CT scan datasets. Then we propose a differentiable neural architecture search (DNAS) framework to automatically search for the 3D DL models for 3D chest CT scans classification with the Gumbel Softmax technique to improve the searching efficiency. We further exploit the Class Activation Mapping (CAM) technique on our models to provide the interpretability of the results. The experimental results show that our automatically searched models (CovidNet3D) outperform the baseline human-designed models on the three datasets with tens of times smaller model size and higher accuracy. Furthermore, the results also verify that CAM can be well applied in CovidNet3D for COVID-19 datasets to provide interpretability for medical diagnosis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.05442v2-abstract-full').style.display = 'none'; document.getElementById('2101.05442v2-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> 12 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </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 AAAI 2021, COVID-19, Neural Architecture Search, AutoML</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.04212">arXiv:2011.04212</a> <span> [<a href="https://arxiv.org/pdf/2011.04212">pdf</a>, <a href="https://arxiv.org/format/2011.04212">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"> PAMS: Quantized Super-Resolution via Parameterized Max Scale </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+H">Huixia Li</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenqian Yan</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+S">Shaohui Lin</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+X">Xiawu Zheng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yuchao Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+B">Baochang Zhang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/eess?searchtype=author&query=Ji%2C+R">Rongrong 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="2011.04212v1-abstract-short" style="display: inline;"> Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on resource-limited devices, which mainly arise from the floating-point storage and operations between weights and activations. Although previous endeavors mainly resort to fixed… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.04212v1-abstract-full').style.display = 'inline'; document.getElementById('2011.04212v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.04212v1-abstract-full" style="display: none;"> Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on resource-limited devices, which mainly arise from the floating-point storage and operations between weights and activations. Although previous endeavors mainly resort to fixed-point operations, quantizing both weights and activations with fixed coding lengths may cause significant performance drop, especially on low bits. Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop. To address these two issues, we propose a new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively. Finally, a structured knowledge transfer (SKT) loss is introduced to fine-tune the quantized network. Extensive experiments demonstrate that the proposed PAMS scheme can well compress and accelerate the existing SR models such as EDSR and RDN. Notably, 8-bit PAMS-EDSR improves PSNR on Set5 benchmark from 32.095dB to 32.124dB with 2.42$\times$ compression ratio, which achieves a new state-of-the-art. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.04212v1-abstract-full').style.display = 'none'; document.getElementById('2011.04212v1-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> 9 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </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">ECCV 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2008.06916">arXiv:2008.06916</a> <span> [<a href="https://arxiv.org/pdf/2008.06916">pdf</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="Medical Physics">physics.med-ph</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1364/OL.400244">10.1364/OL.400244 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Virtual brightfield and fluorescence staining for Fourier ptychography via unsupervised deep learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+R">Ruihai Wang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+P">Pengming Song</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+S">Shaowei Jiang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+J">Jiakai Zhu</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+C">Chengfei Guo</a>, <a href="/search/eess?searchtype=author&query=Bian%2C+Z">Zichao Bian</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+T">Tianbo Wang</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+G">Guoan 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="2008.06916v1-abstract-short" style="display: inline;"> Fourier ptychographic microscopy (FPM) is a computational approach geared towards creating high-resolution and large field-of-view images without mechanical scanning. To acquire color images of histology slides, it often requires sequential acquisitions with red, green, and blue illuminations. The color reconstructions often suffer from coherent artifacts that are not presented in regular incohere… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.06916v1-abstract-full').style.display = 'inline'; document.getElementById('2008.06916v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.06916v1-abstract-full" style="display: none;"> Fourier ptychographic microscopy (FPM) is a computational approach geared towards creating high-resolution and large field-of-view images without mechanical scanning. To acquire color images of histology slides, it often requires sequential acquisitions with red, green, and blue illuminations. The color reconstructions often suffer from coherent artifacts that are not presented in regular incoherent microscopy images. As a result, it remains a challenge to employ FPM for digital pathology applications, where resolution and color accuracy are of critical importance. Here we report a deep learning approach for performing unsupervised image-to-image translation of FPM reconstructions. A cycle-consistent adversarial network with multiscale structure similarity loss is trained to perform virtual brightfield and fluorescence staining of the recovered FPM images. In the training stage, we feed the network with two sets of unpaired images: 1) monochromatic FPM recovery, and 2) color or fluorescence images captured using a regular microscope. In the inference stage, the network takes the FPM input and outputs a virtually stained image with reduced coherent artifacts and improved image quality. We test the approach on various samples with different staining protocols. High-quality color and fluorescence reconstructions validate its effectiveness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.06916v1-abstract-full').style.display = 'none'; document.getElementById('2008.06916v1-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 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.00169">arXiv:2002.00169</a> <span> [<a href="https://arxiv.org/pdf/2002.00169">pdf</a>, <a href="https://arxiv.org/format/2002.00169">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="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Deep Multi-View Enhancement Hashing for Image Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+B">Biao Gong</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+Y">Yuxuan Wei</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yue Gao</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="2002.00169v2-abstract-short" style="display: inline;"> Hashing is an efficient method for nearest neighbor search in large-scale data space by embedding high-dimensional feature descriptors into a similarity preserving Hamming space with a low dimension. However, large-scale high-speed retrieval through binary code has a certain degree of reduction in retrieval accuracy compared to traditional retrieval methods. We have noticed that multi-view methods… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.00169v2-abstract-full').style.display = 'inline'; document.getElementById('2002.00169v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.00169v2-abstract-full" style="display: none;"> Hashing is an efficient method for nearest neighbor search in large-scale data space by embedding high-dimensional feature descriptors into a similarity preserving Hamming space with a low dimension. However, large-scale high-speed retrieval through binary code has a certain degree of reduction in retrieval accuracy compared to traditional retrieval methods. We have noticed that multi-view methods can well preserve the diverse characteristics of data. Therefore, we try to introduce the multi-view deep neural network into the hash learning field, and design an efficient and innovative retrieval model, which has achieved a significant improvement in retrieval performance. In this paper, we propose a supervised multi-view hash model which can enhance the multi-view information through neural networks. This is a completely new hash learning method that combines multi-view and deep learning methods. The proposed method utilizes an effective view stability evaluation method to actively explore the relationship among views, which will affect the optimization direction of the entire network. We have also designed a variety of multi-data fusion methods in the Hamming space to preserve the advantages of both convolution and multi-view. In order to avoid excessive computing resources on the enhancement procedure during retrieval, we set up a separate structure called memory network which participates in training together. The proposed method is systematically evaluated on the CIFAR-10, NUS-WIDE and MS-COCO datasets, and the results show that our method significantly outperforms the state-of-the-art single-view and multi-view hashing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.00169v2-abstract-full').style.display = 'none'; document.getElementById('2002.00169v2-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 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.00402">arXiv:1912.00402</a> <span> [<a href="https://arxiv.org/pdf/1912.00402">pdf</a>, <a href="https://arxiv.org/format/1912.00402">other</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="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.23919/DATE.2019.8714788">10.23919/DATE.2019.8714788 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Bayesian Optimization Approach for Analog Circuit Synthesis Using Neural Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shuhan Zhang</a>, <a href="/search/eess?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Changhao Yan</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+D">Dian Zhou</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+X">Xuan Zeng</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="1912.00402v1-abstract-short" style="display: inline;"> Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis. In the traditional Gaussian process regression model, the kernel functions are defined explicitly. The computational complexity of training is O(N 3 ), and the computation complexity of prediction is O(N 2 ), where N is the number of training data. Gaussian process model can al… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00402v1-abstract-full').style.display = 'inline'; document.getElementById('1912.00402v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.00402v1-abstract-full" style="display: none;"> Bayesian optimization with Gaussian process as surrogate model has been successfully applied to analog circuit synthesis. In the traditional Gaussian process regression model, the kernel functions are defined explicitly. The computational complexity of training is O(N 3 ), and the computation complexity of prediction is O(N 2 ), where N is the number of training data. Gaussian process model can also be derived from a weight space view, where the original data are mapped to feature space, and the kernel function is defined as the inner product of nonlinear features. In this paper, we propose a Bayesian optimization approach for analog circuit synthesis using neural network. We use deep neural network to extract good feature representations, and then define Gaussian process using the extracted features. Model averaging method is applied to improve the quality of uncertainty prediction. Compared to Gaussian process model with explicitly defined kernel functions, the neural-network-based Gaussian process model can automatically learn a kernel function from data, which makes it possible to provide more accurate predictions and thus accelerate the follow-up optimization procedure. Also, the neural-network-based model has O(N) training time and constant prediction time. The efficiency of the proposed method has been verified by two real-world analog circuits. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00402v1-abstract-full').style.display = 'none'; document.getElementById('1912.00402v1-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> 1 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.00392">arXiv:1912.00392</a> <span> [<a href="https://arxiv.org/pdf/1912.00392">pdf</a>, <a href="https://arxiv.org/format/1912.00392">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 class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3316781.3317765">10.1145/3316781.3317765 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An Efficient Multi-fidelity Bayesian Optimization Approach for Analog Circuit Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shuhan Zhang</a>, <a href="/search/eess?searchtype=author&query=Lyu%2C+W">Wenlong Lyu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fan Yang</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Changhao Yan</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+D">Dian Zhou</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+X">Xuan Zeng</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+X">Xiangdong Hu</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="1912.00392v1-abstract-short" style="display: inline;"> This paper presents an efficient multi-fidelity Bayesian optimization approach for analog circuit synthesis. The proposed method can significantly reduce the overall computational cost by fusing the simple but potentially inaccurate low-fidelity model and a few accurate but expensive high-fidelity data. Gaussian Process (GP) models are employed to model the low- and high-fidelity black-box functio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00392v1-abstract-full').style.display = 'inline'; document.getElementById('1912.00392v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.00392v1-abstract-full" style="display: none;"> This paper presents an efficient multi-fidelity Bayesian optimization approach for analog circuit synthesis. The proposed method can significantly reduce the overall computational cost by fusing the simple but potentially inaccurate low-fidelity model and a few accurate but expensive high-fidelity data. Gaussian Process (GP) models are employed to model the low- and high-fidelity black-box functions separately. The nonlinear map between the low-fidelity model and high-fidelity model is also modelled as a Gaussian process. A fusing GP model which combines the low- and high-fidelity models can thus be built. An acquisition function based on the fusing GP model is used to balance the exploitation and exploration. The fusing GP model is evolved gradually as new data points are selected sequentially by maximizing the acquisition function. Experimental results show that our proposed method reduces up to 65.5\% of the simulation time compared with the state-of-the-art single-fidelity Bayesian optimization method, while exhibiting more stable performance and a more promising practical prospect. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.00392v1-abstract-full').style.display = 'none'; document.getElementById('1912.00392v1-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> 1 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> The 56th Annual Design Automation Conference 2019 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.02526">arXiv:1911.02526</a> <span> [<a href="https://arxiv.org/pdf/1911.02526">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biological Physics">physics.bio-ph</span> <span class="tag is-small is-grey 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="Quantitative Methods">q-bio.QM</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1088/1748-3190/aaa2cd">10.1088/1748-3190/aaa2cd <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Dynamic traversal of large gaps by insects and legged robots reveals a template </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gart%2C+S+W">Sean W. Gart</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Changxin Yan</a>, <a href="/search/eess?searchtype=author&query=Othayoth%2C+R">Ratan Othayoth</a>, <a href="/search/eess?searchtype=author&query=Ren%2C+Z">Zhiyi Ren</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Chen 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="1911.02526v1-abstract-short" style="display: inline;"> It is well known that animals can use neural and sensory feedback via vision, tactile sensing, and echolocation to negotiate obstacles. Similarly, most robots use deliberate or reactive planning to avoid obstacles, which relies on prior knowledge or high-fidelity sensing of the environment. However, during dynamic locomotion in complex, novel, 3-D terrains such as forest floor and building rubble,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.02526v1-abstract-full').style.display = 'inline'; document.getElementById('1911.02526v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.02526v1-abstract-full" style="display: none;"> It is well known that animals can use neural and sensory feedback via vision, tactile sensing, and echolocation to negotiate obstacles. Similarly, most robots use deliberate or reactive planning to avoid obstacles, which relies on prior knowledge or high-fidelity sensing of the environment. However, during dynamic locomotion in complex, novel, 3-D terrains such as forest floor and building rubble, sensing and planning suffer bandwidth limitation and large noise and are sometimes even impossible. Here, we study rapid locomotion over a large gap, a simple, ubiquitous obstacle, to begin to discover general principles of dynamic traversal of large 3-D obstacles. We challenged the discoid cockroach and an open-loop six-legged robot to traverse a large gap of varying length. Both the animal and the robot could dynamically traverse a gap as large as 1 body length by bridging the gap with its head, but traversal probability decreased with gap length. Based on these observations, we developed a template that well captured body dynamics and quantitatively predicted traversal performance. Our template revealed that high approach speed, initial body pitch, and initial body pitch angular velocity facilitated dynamic traversal, and successfully predicted a new strategy of using body pitch control that increased the robot maximal traversal gap length by 50%. Our study established the first template of dynamic locomotion beyond planar surfaces and is an important step in expanding terradynamics into complex 3-D terrains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.02526v1-abstract-full').style.display = 'none'; document.getElementById('1911.02526v1-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> 1 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Bioinspiration & Biomimetics (2018), 13, 026006 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.04399">arXiv:1905.04399</a> <span> [<a href="https://arxiv.org/pdf/1905.04399">pdf</a>, <a href="https://arxiv.org/format/1905.04399">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 New Encounter Between Leader-Follower Tracking and Observer-Based Control: Towards Enhancing Robustness against Disturbances </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chuan Yan</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+H">Huazhen Fang</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="1905.04399v1-abstract-short" style="display: inline;"> This paper studies robust tracking control for a leader-follower multi-agent system (MAS) subject to disturbances. A challenging problem is considered here, which differs from those in the literature in two aspects. First, we consider the case when all the leader and follower agents are affected by disturbances, while the existing studies assume only the followers to suffer disturbances. Second, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.04399v1-abstract-full').style.display = 'inline'; document.getElementById('1905.04399v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.04399v1-abstract-full" style="display: none;"> This paper studies robust tracking control for a leader-follower multi-agent system (MAS) subject to disturbances. A challenging problem is considered here, which differs from those in the literature in two aspects. First, we consider the case when all the leader and follower agents are affected by disturbances, while the existing studies assume only the followers to suffer disturbances. Second, we assume the disturbances to be bounded only in rates of change rather than magnitude as in the literature. To address this new problem, we propose a novel observer-based distributed tracking control design. As a distinguishing feature, the followers can cooperatively estimate the disturbance affecting the leader to adjust their maneuvers accordingly, which is enabled by the design of the first-of-its-kind distributed disturbance observers. We build specific tracking control approaches for both first- and second-order MASs and prove that they can lead to bounded-error tracking, despite the challenges due to the relaxed assumptions about disturbances. We further perform simulation to validate the proposed approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.04399v1-abstract-full').style.display = 'none'; document.getElementById('1905.04399v1-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 May, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1904.00338">arXiv:1904.00338</a> <span> [<a href="https://arxiv.org/pdf/1904.00338">pdf</a>, <a href="https://arxiv.org/format/1904.00338">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 class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1080/00207179.2019.1580770">10.1080/00207179.2019.1580770 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Observer-Based Distributed Leader-Follower Tracking Control: A New Perspective and Results </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chuan Yan</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+H">Huazhen Fang</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="1904.00338v1-abstract-short" style="display: inline;"> Leader-follower tracking control design has received significant attention in recent years due to its important and wide applications. Considering a multi-agent system composed of a leader and multiple followers, this paper proposes and investigates a new perspective into this problem: can we enable a follower to estimate the leader's driving input and leverage this idea to develop new observer-ba… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.00338v1-abstract-full').style.display = 'inline'; document.getElementById('1904.00338v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1904.00338v1-abstract-full" style="display: none;"> Leader-follower tracking control design has received significant attention in recent years due to its important and wide applications. Considering a multi-agent system composed of a leader and multiple followers, this paper proposes and investigates a new perspective into this problem: can we enable a follower to estimate the leader's driving input and leverage this idea to develop new observer-based tracking control approaches? With this motivation, we develop an input-observer-based leader-follower tracking control framework, which features distributed input observers that allow a follower to locally estimate the leader's input toward enhancing tracking control. This work first studies the first-order tracking problem. It then extends to the more sophisticated case of second-order tracking and considers a challenging situation when the leader's and followers' velocities are not measured. The proposed approaches exhibit interesting and useful advantages as revealed by a comparison with the literature. Convergence properties of the proposed approaches are rigorously analyzed. Simulation results further illustrate the efficacy of the proposed perspective, framework and approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1904.00338v1-abstract-full').style.display = 'none'; document.getElementById('1904.00338v1-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> 31 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2019. </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">International Journal of Control 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1401.2181">arXiv:1401.2181</a> <span> [<a href="https://arxiv.org/pdf/1401.2181">pdf</a>, <a href="https://arxiv.org/ps/1401.2181">ps</a>, <a href="https://arxiv.org/format/1401.2181">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="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> A biologically inspired model for transshipment problem </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gao%2C+C">Cai Gao</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+C">Chao Yan</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+D">Daijun Wei</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Y">Yong Hu</a>, <a href="/search/eess?searchtype=author&query=Mahadevan%2C+S">Sankaran Mahadevan</a>, <a href="/search/eess?searchtype=author&query=Deng%2C+Y">Yong Deng</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="1401.2181v1-abstract-short" style="display: inline;"> Transshipment problem is one of the basic operational research problems. In this paper, our first work is to develop a biologically inspired mathematical model for a dynamical system, which is first used to solve minimum cost flow problem. It has lower computational complexity than Physarum Solver. Second, we apply the proposed model to solve the traditional transshipment problem. Compared with th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1401.2181v1-abstract-full').style.display = 'inline'; document.getElementById('1401.2181v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1401.2181v1-abstract-full" style="display: none;"> Transshipment problem is one of the basic operational research problems. In this paper, our first work is to develop a biologically inspired mathematical model for a dynamical system, which is first used to solve minimum cost flow problem. It has lower computational complexity than Physarum Solver. Second, we apply the proposed model to solve the traditional transshipment problem. Compared with the conditional methods, experiment results show the provided model is simple, effective as well as handling problem in a continuous manner. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1401.2181v1-abstract-full').style.display = 'none'; document.getElementById('1401.2181v1-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, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2014. </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">4 pages, 2 figures</span> </p> </li> </ol> <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