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 1–20 of 20 results for author: <span class="mathjax">Wan, S</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=Wan%2C+S">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="Wan, S"> </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=Wan%2C+S&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="Wan, S"> <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/2408.14977">arXiv:2408.14977</a> <span> [<a href="https://arxiv.org/pdf/2408.14977">pdf</a>, <a href="https://arxiv.org/format/2408.14977">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"> LN-Gen: Rectal Lymph Nodes Generation via Anatomical Features </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Guo%2C+W">Weidong Guo</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Hantao Zhang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shouhong Wan</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+B">Bingbing Zou</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wanqin Wang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+P">Peiquan Jin</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="2408.14977v1-abstract-short" style="display: inline;"> Accurate segmentation of rectal lymph nodes is crucial for the staging and treatment planning of rectal cancer. However, the complexity of the surrounding anatomical structures and the scarcity of annotated data pose significant challenges. This study introduces a novel lymph node synthesis technique aimed at generating diverse and realistic synthetic rectal lymph node samples to mitigate the reli… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14977v1-abstract-full').style.display = 'inline'; document.getElementById('2408.14977v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.14977v1-abstract-full" style="display: none;"> Accurate segmentation of rectal lymph nodes is crucial for the staging and treatment planning of rectal cancer. However, the complexity of the surrounding anatomical structures and the scarcity of annotated data pose significant challenges. This study introduces a novel lymph node synthesis technique aimed at generating diverse and realistic synthetic rectal lymph node samples to mitigate the reliance on manual annotation. Unlike direct diffusion methods, which often produce masks that are discontinuous and of suboptimal quality, our approach leverages an implicit SDF-based method for mask generation, ensuring the production of continuous, stable, and morphologically diverse masks. Experimental results demonstrate that our synthetic data significantly improves segmentation performance. Our work highlights the potential of diffusion model for accurately synthesizing structurally complex lesions, such as lymph nodes in rectal cancer, alleviating the challenge of limited annotated data in this field and aiding in advancements in rectal cancer diagnosis and treatment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.14977v1-abstract-full').style.display = 'none'; document.getElementById('2408.14977v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.16398">arXiv:2405.16398</a> <span> [<a href="https://arxiv.org/pdf/2405.16398">pdf</a>, <a href="https://arxiv.org/format/2405.16398">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Networked Integrated Sensing and Communications for 6G Wireless Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+J">Jiapeng Li</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+X">Xiaodan Shao</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+F">Feng Chen</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shaohua Wan</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+C">Chang Liu</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+Z">Zhiqiang Wei</a>, <a href="/search/eess?searchtype=author&query=Ng%2C+D+W+K">Derrick Wing Kwan Ng</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="2405.16398v1-abstract-short" style="display: inline;"> Integrated sensing and communication (ISAC) is envisioned as a key pillar for enabling the upcoming sixth generation (6G) communication systems, requiring not only reliable communication functionalities but also highly accurate environmental sensing capabilities. In this paper, we design a novel networked ISAC framework to explore the collaboration among multiple users for environmental sensing. S… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16398v1-abstract-full').style.display = 'inline'; document.getElementById('2405.16398v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.16398v1-abstract-full" style="display: none;"> Integrated sensing and communication (ISAC) is envisioned as a key pillar for enabling the upcoming sixth generation (6G) communication systems, requiring not only reliable communication functionalities but also highly accurate environmental sensing capabilities. In this paper, we design a novel networked ISAC framework to explore the collaboration among multiple users for environmental sensing. Specifically, multiple users can serve as powerful sensors, capturing back scattered signals from a target at various angles to facilitate reliable computational imaging. Centralized sensing approaches are extremely sensitive to the capability of the leader node because it requires the leader node to process the signals sent by all the users. To this end, we propose a two-step distributed cooperative sensing algorithm that allows low-dimensional intermediate estimate exchange among neighboring users, thus eliminating the reliance on the centralized leader node and improving the robustness of sensing. This way, multiple users can cooperatively sense a target by exploiting the block-wise environment sparsity and the interference cancellation technique. Furthermore, we analyze the mean square error of the proposed distributed algorithm as a networked sensing performance metric and propose a beamforming design for the proposed network ISAC scheme to maximize the networked sensing accuracy and communication performance subject to a transmit power constraint. Simulation results validate the effectiveness of the proposed algorithm compared with the state-of-the-art algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16398v1-abstract-full').style.display = 'none'; document.getElementById('2405.16398v1-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 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">Received by IEEE Internet of Things Journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.14066">arXiv:2403.14066</a> <span> [<a href="https://arxiv.org/pdf/2403.14066">pdf</a>, <a href="https://arxiv.org/format/2403.14066">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"> LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Hantao Zhang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yuhe Liu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jiancheng Yang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shouhong Wan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xinyuan Wang</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+W">Wei Peng</a>, <a href="/search/eess?searchtype=author&query=Fua%2C+P">Pascal Fua</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="2403.14066v2-abstract-short" style="display: inline;"> Patient data from real-world clinical practice often suffers from data scarcity and long-tail imbalances, leading to biased outcomes or algorithmic unfairness. This study addresses these challenges by generating lesion-containing image-segmentation pairs from lesion-free images. Previous efforts in medical imaging synthesis have struggled with separating lesion information from background, resulti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14066v2-abstract-full').style.display = 'inline'; document.getElementById('2403.14066v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.14066v2-abstract-full" style="display: none;"> Patient data from real-world clinical practice often suffers from data scarcity and long-tail imbalances, leading to biased outcomes or algorithmic unfairness. This study addresses these challenges by generating lesion-containing image-segmentation pairs from lesion-free images. Previous efforts in medical imaging synthesis have struggled with separating lesion information from background, resulting in low-quality backgrounds and limited control over the synthetic output. Inspired by diffusion-based image inpainting, we propose LeFusion, a lesion-focused diffusion model. By redesigning the diffusion learning objectives to focus on lesion areas, we simplify the learning process and improve control over the output while preserving high-fidelity backgrounds by integrating forward-diffused background contexts into the reverse diffusion process. Additionally, we tackle two major challenges in lesion texture synthesis: 1) multi-peak and 2) multi-class lesions. We introduce two effective strategies: histogram-based texture control and multi-channel decomposition, enabling the controlled generation of high-quality lesions in difficult scenarios. Furthermore, we incorporate lesion mask diffusion, allowing control over lesion size, location, and boundary, thus increasing lesion diversity. Validated on 3D cardiac lesion MRI and lung nodule CT datasets, LeFusion-generated data significantly improves the performance of state-of-the-art segmentation models, including nnUNet and SwinUNETR. Code and model are available at https://github.com/M3DV/LeFusion. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14066v2-abstract-full').style.display = 'none'; document.getElementById('2403.14066v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">19 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.08283">arXiv:2308.08283</a> <span> [<a href="https://arxiv.org/pdf/2308.08283">pdf</a>, <a href="https://arxiv.org/format/2308.08283">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"> CARE: A Large Scale CT Image Dataset and Clinical Applicable Benchmark Model for Rectal Cancer Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Hantao Zhang</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+W">Weidong Guo</a>, <a href="/search/eess?searchtype=author&query=Qiu%2C+C">Chenyang Qiu</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shouhong Wan</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+B">Bingbing Zou</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wanqin Wang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+P">Peiquan Jin</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="2308.08283v1-abstract-short" style="display: inline;"> Rectal cancer segmentation of CT image plays a crucial role in timely clinical diagnosis, radiotherapy treatment, and follow-up. Although current segmentation methods have shown promise in delineating cancerous tissues, they still encounter challenges in achieving high segmentation precision. These obstacles arise from the intricate anatomical structures of the rectum and the difficulties in perfo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08283v1-abstract-full').style.display = 'inline'; document.getElementById('2308.08283v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.08283v1-abstract-full" style="display: none;"> Rectal cancer segmentation of CT image plays a crucial role in timely clinical diagnosis, radiotherapy treatment, and follow-up. Although current segmentation methods have shown promise in delineating cancerous tissues, they still encounter challenges in achieving high segmentation precision. These obstacles arise from the intricate anatomical structures of the rectum and the difficulties in performing differential diagnosis of rectal cancer. Additionally, a major obstacle is the lack of a large-scale, finely annotated CT image dataset for rectal cancer segmentation. To address these issues, this work introduces a novel large scale rectal cancer CT image dataset CARE with pixel-level annotations for both normal and cancerous rectum, which serves as a valuable resource for algorithm research and clinical application development. Moreover, we propose a novel medical cancer lesion segmentation benchmark model named U-SAM. The model is specifically designed to tackle the challenges posed by the intricate anatomical structures of abdominal organs by incorporating prompt information. U-SAM contains three key components: promptable information (e.g., points) to aid in target area localization, a convolution module for capturing low-level lesion details, and skip-connections to preserve and recover spatial information during the encoding-decoding process. To evaluate the effectiveness of U-SAM, we systematically compare its performance with several popular segmentation methods on the CARE dataset. The generalization of the model is further verified on the WORD dataset. Extensive experiments demonstrate that the proposed U-SAM outperforms state-of-the-art methods on these two datasets. These experiments can serve as the baseline for future research and clinical application development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08283v1-abstract-full').style.display = 'none'; document.getElementById('2308.08283v1-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, 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">8 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.00009">arXiv:2308.00009</a> <span> [<a href="https://arxiv.org/pdf/2308.00009">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> A 3D deep learning classifier and its explainability when assessing coronary artery disease </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Cheung%2C+W+K">Wing Keung Cheung</a>, <a href="/search/eess?searchtype=author&query=Kalindjian%2C+J">Jeremy Kalindjian</a>, <a href="/search/eess?searchtype=author&query=Bell%2C+R">Robert Bell</a>, <a href="/search/eess?searchtype=author&query=Nair%2C+A">Arjun Nair</a>, <a href="/search/eess?searchtype=author&query=Menezes%2C+L+J">Leon J. Menezes</a>, <a href="/search/eess?searchtype=author&query=Patel%2C+R">Riyaz Patel</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Simon Wan</a>, <a href="/search/eess?searchtype=author&query=Chou%2C+K">Kacy Chou</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jiahang Chen</a>, <a href="/search/eess?searchtype=author&query=Torii%2C+R">Ryo Torii</a>, <a href="/search/eess?searchtype=author&query=Davies%2C+R+H">Rhodri H. Davies</a>, <a href="/search/eess?searchtype=author&query=Moon%2C+J+C">James C. Moon</a>, <a href="/search/eess?searchtype=author&query=Alexander%2C+D+C">Daniel C. Alexander</a>, <a href="/search/eess?searchtype=author&query=Jacob%2C+J">Joseph Jacob</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="2308.00009v2-abstract-short" style="display: inline;"> Early detection and diagnosis of coronary artery disease (CAD) could save lives and reduce healthcare costs. The current clinical practice is to perform CAD diagnosis through analysing medical images from computed tomography coronary angiography (CTCA). Most current approaches utilise deep learning methods but require centerline extraction and multi-planar reconstruction. These indirect methods ar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.00009v2-abstract-full').style.display = 'inline'; document.getElementById('2308.00009v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.00009v2-abstract-full" style="display: none;"> Early detection and diagnosis of coronary artery disease (CAD) could save lives and reduce healthcare costs. The current clinical practice is to perform CAD diagnosis through analysing medical images from computed tomography coronary angiography (CTCA). Most current approaches utilise deep learning methods but require centerline extraction and multi-planar reconstruction. These indirect methods are not designed in a clinician-friendly manner, and they complicate the interventional procedure. Furthermore, the current deep learning methods do not provide exact explainability and limit the usefulness of these methods to be deployed in clinical settings. In this study, we first propose a 3D Resnet-50 deep learning model to directly classify normal subjects and CAD patients on CTCA images, then we demonstrate a 2D modified U-Net model can be subsequently employed to segment the coronary arteries. Our proposed approach outperforms the state-of-the-art models by 21.43% in terms of classification accuracy. The classification model with focal loss provides a better and more focused heat map, and the segmentation model provides better explainability than the classification-only model. The proposed holistic approach not only provides a simpler and clinician-friendly solution but also good classification accuracy and exact explainability for CAD diagnosis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.00009v2-abstract-full').style.display = 'none'; document.getElementById('2308.00009v2-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.10167">arXiv:2301.10167</a> <span> [<a href="https://arxiv.org/pdf/2301.10167">pdf</a>, <a href="https://arxiv.org/format/2301.10167">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optics">physics.optics</span> </div> </div> <p class="title is-5 mathjax"> EEG Opto-processor: epileptic seizure detection using diffractive photonic computing units </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yan%2C+T">Tao Yan</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+M">Maoqi Zhang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Sen Wan</a>, <a href="/search/eess?searchtype=author&query=Shang%2C+K">Kaifeng Shang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Haiou Zhang</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+X">Xun Cao</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+X">Xing Lin</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+Q">Qionghai Dai</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="2301.10167v1-abstract-short" style="display: inline;"> Electroencephalography (EEG) analysis extracts critical information from brain signals, which has provided fundamental support for various applications, including brain-disease diagnosis and brain-computer interface. However, the real-time processing of large-scale EEG signals at high energy efficiency has placed great challenges for electronic processors on edge computing devices. Here, we propos… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.10167v1-abstract-full').style.display = 'inline'; document.getElementById('2301.10167v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.10167v1-abstract-full" style="display: none;"> Electroencephalography (EEG) analysis extracts critical information from brain signals, which has provided fundamental support for various applications, including brain-disease diagnosis and brain-computer interface. However, the real-time processing of large-scale EEG signals at high energy efficiency has placed great challenges for electronic processors on edge computing devices. Here, we propose the EEG opto-processor based on diffractive photonic computing units (DPUs) to effectively process the extracranial and intracranial EEG signals and perform epileptic seizure detection. The signals of EEG channels within a second-time window are optically encoded as inputs to the constructed diffractive neural networks for classification, which monitors the brain state to determine whether it's the symptom of an epileptic seizure or not. We developed both the free-space and integrated DPUs as edge computing systems and demonstrated their applications for real-time epileptic seizure detection with the benchmark datasets, i.e., the CHB-MIT extracranial EEG dataset and Epilepsy-iEEG-Multicenter intracranial EEG dataset, at high computing performance. Along with the channel selection mechanism, both the numerical evaluations and experimental results validated the sufficient high classification accuracies of the proposed opto-processors for supervising the clinical diagnosis. Our work opens up a new research direction of utilizing photonic computing techniques for processing large-scale EEG signals in promoting its broader applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.10167v1-abstract-full').style.display = 'none'; document.getElementById('2301.10167v1-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 December, 2022; <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">22 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/2206.07893">arXiv:2206.07893</a> <span> [<a href="https://arxiv.org/pdf/2206.07893">pdf</a>, <a href="https://arxiv.org/format/2206.07893">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> PeQuENet: Perceptual Quality Enhancement of Compressed Video with Adaptation- and Attention-based Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Saiping Zhang</a>, <a href="/search/eess?searchtype=author&query=Herranz%2C+L">Luis Herranz</a>, <a href="/search/eess?searchtype=author&query=Mrak%2C+M">Marta Mrak</a>, <a href="/search/eess?searchtype=author&query=Blanch%2C+M+G">Marc Gorriz Blanch</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuai Wan</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fuzheng Yang</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="2206.07893v1-abstract-short" style="display: inline;"> In this paper we propose a generative adversarial network (GAN) framework to enhance the perceptual quality of compressed videos. Our framework includes attention and adaptation to different quantization parameters (QPs) in a single model. The attention module exploits global receptive fields that can capture and align long-range correlations between consecutive frames, which can be beneficial for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.07893v1-abstract-full').style.display = 'inline'; document.getElementById('2206.07893v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.07893v1-abstract-full" style="display: none;"> In this paper we propose a generative adversarial network (GAN) framework to enhance the perceptual quality of compressed videos. Our framework includes attention and adaptation to different quantization parameters (QPs) in a single model. The attention module exploits global receptive fields that can capture and align long-range correlations between consecutive frames, which can be beneficial for enhancing perceptual quality of videos. The frame to be enhanced is fed into the deep network together with its neighboring frames, and in the first stage features at different depths are extracted. Then extracted features are fed into attention blocks to explore global temporal correlations, followed by a series of upsampling and convolution layers. Finally, the resulting features are processed by the QP-conditional adaptation module which leverages the corresponding QP information. In this way, a single model can be used to enhance adaptively to various QPs without requiring multiple models specific for every QP value, while having similar performance. Experimental results demonstrate the superior performance of the proposed PeQuENet compared with the state-of-the-art compressed video quality enhancement algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.07893v1-abstract-full').style.display = 'none'; document.getElementById('2206.07893v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.06754">arXiv:2205.06754</a> <span> [<a href="https://arxiv.org/pdf/2205.06754">pdf</a>, <a href="https://arxiv.org/format/2205.06754">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"> Slimmable Video Codec </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zhaocheng Liu</a>, <a href="/search/eess?searchtype=author&query=Herranz%2C+L">Luis Herranz</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fei Yang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Saiping Zhang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuai Wan</a>, <a href="/search/eess?searchtype=author&query=Mrak%2C+M">Marta Mrak</a>, <a href="/search/eess?searchtype=author&query=Blanch%2C+M+G">Marc G贸rriz Blanch</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="2205.06754v1-abstract-short" style="display: inline;"> Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands. In addition, models are usually optimized for a single RD tradeoff. Recent slimmable image codecs can dyn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.06754v1-abstract-full').style.display = 'inline'; document.getElementById('2205.06754v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.06754v1-abstract-full" style="display: none;"> Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands. In addition, models are usually optimized for a single RD tradeoff. Recent slimmable image codecs can dynamically adjust their model capacity to gracefully reduce the memory and computation requirements, without harming RD performance. In this paper we propose a slimmable video codec (SlimVC), by integrating a slimmable temporal entropy model in a slimmable autoencoder. Despite a significantly more complex architecture, we show that slimming remains a powerful mechanism to control rate, memory footprint, computational cost and latency, all being important requirements for practical video compression. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.06754v1-abstract-full').style.display = 'none'; document.getElementById('2205.06754v1-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 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">Computer Vision and Pattern Recognition Workshop(CLIC2022)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.03380">arXiv:2205.03380</a> <span> [<a href="https://arxiv.org/pdf/2205.03380">pdf</a>, <a href="https://arxiv.org/ps/2205.03380">ps</a>, <a href="https://arxiv.org/format/2205.03380">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="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Multi-mode Tensor Train Factorization with Spatial-spectral Regularization for Remote Sensing Images Recovery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+G">Gaohang Yu</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shaochun Wan</a>, <a href="/search/eess?searchtype=author&query=Qi%2C+L">Liqun Qi</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yanwei 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="2205.03380v1-abstract-short" style="display: inline;"> Tensor train (TT) factorization and corresponding TT rank, which can well express the low-rankness and mode correlations of higher-order tensors, have attracted much attention in recent years. However, TT factorization based methods are generally not sufficient to characterize low-rankness along each mode of third-order tensor. Inspired by this, we generalize the tensor train factorization to the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.03380v1-abstract-full').style.display = 'inline'; document.getElementById('2205.03380v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.03380v1-abstract-full" style="display: none;"> Tensor train (TT) factorization and corresponding TT rank, which can well express the low-rankness and mode correlations of higher-order tensors, have attracted much attention in recent years. However, TT factorization based methods are generally not sufficient to characterize low-rankness along each mode of third-order tensor. Inspired by this, we generalize the tensor train factorization to the mode-k tensor train factorization and introduce a corresponding multi-mode tensor train (MTT) rank. Then, we proposed a novel low-MTT-rank tensor completion model via multi-mode TT factorization and spatial-spectral smoothness regularization. To tackle the proposed model, we develop an efficient proximal alternating minimization (PAM) algorithm. Extensive numerical experiment results on visual data demonstrate that the proposed MTTD3R method outperforms compared methods in terms of visual and quantitative measures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.03380v1-abstract-full').style.display = 'none'; document.getElementById('2205.03380v1-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 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">21 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.08944">arXiv:2201.08944</a> <span> [<a href="https://arxiv.org/pdf/2201.08944">pdf</a>, <a href="https://arxiv.org/format/2201.08944">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> DCNGAN: A Deformable Convolutional-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Saiping Zhang</a>, <a href="/search/eess?searchtype=author&query=Herranz%2C+L">Luis Herranz</a>, <a href="/search/eess?searchtype=author&query=Mrak%2C+M">Marta Mrak</a>, <a href="/search/eess?searchtype=author&query=Blanch%2C+M+G">Marc Gorriz Blanch</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuai Wan</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fuzheng Yang</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="2201.08944v3-abstract-short" style="display: inline;"> In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.08944v3-abstract-full').style.display = 'inline'; document.getElementById('2201.08944v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.08944v3-abstract-full" style="display: none;"> In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical flows, deformable convolutions are more effective and efficient to align frames. Deformable convolutions can operate on multiple frames, thus leveraging more temporal information, which is beneficial for enhancing the perceptual quality of compressed videos. Instead of aligning frames in a pairwise manner, the deformable convolution can process multiple frames simultaneously, which leads to lower computational complexity. Experimental results demonstrate that the proposed DCNGAN outperforms other state-of-the-art compressed video quality enhancement algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.08944v3-abstract-full').style.display = 'none'; document.getElementById('2201.08944v3-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">5 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/2109.10849">arXiv:2109.10849</a> <span> [<a href="https://arxiv.org/pdf/2109.10849">pdf</a>, <a href="https://arxiv.org/format/2109.10849">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> DVC-P: Deep Video Compression with Perceptual Optimizations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Saiping Zhang</a>, <a href="/search/eess?searchtype=author&query=Mrak%2C+M">Marta Mrak</a>, <a href="/search/eess?searchtype=author&query=Herranz%2C+L">Luis Herranz</a>, <a href="/search/eess?searchtype=author&query=G%C3%B3rriz%2C+M">Marc G贸rriz</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuai Wan</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fuzheng Yang</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="2109.10849v2-abstract-short" style="display: inline;"> Recent years have witnessed the significant development of learning-based video compression methods, which aim at optimizing objective or perceptual quality and bit rates. In this paper, we introduce deep video compression with perceptual optimizations (DVC-P), which aims at increasing perceptual quality of decoded videos. Our proposed DVC-P is based on Deep Video Compression (DVC) network, but im… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.10849v2-abstract-full').style.display = 'inline'; document.getElementById('2109.10849v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.10849v2-abstract-full" style="display: none;"> Recent years have witnessed the significant development of learning-based video compression methods, which aim at optimizing objective or perceptual quality and bit rates. In this paper, we introduce deep video compression with perceptual optimizations (DVC-P), which aims at increasing perceptual quality of decoded videos. Our proposed DVC-P is based on Deep Video Compression (DVC) network, but improves it with perceptual optimizations. Specifically, a discriminator network and a mixed loss are employed to help our network trade off among distortion, perception and rate. Furthermore, nearest-neighbor interpolation is used to eliminate checkerboard artifacts which can appear in sequences encoded with DVC frameworks. Thanks to these two improvements, the perceptual quality of decoded sequences is improved. Experimental results demonstrate that, compared with the baseline DVC, our proposed method can generate videos with higher perceptual quality achieving 12.27% reduction in a perceptual BD-rate equivalent, on average. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.10849v2-abstract-full').style.display = 'none'; document.getElementById('2109.10849v2-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 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2003.03756">arXiv:2003.03756</a> <span> [<a href="https://arxiv.org/pdf/2003.03756">pdf</a>, <a href="https://arxiv.org/format/2003.03756">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"> Perceptual Image Super-Resolution with Progressive Adversarial Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wong%2C+L">Lone Wong</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+D">Deli Zhao</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shaohua Wan</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+B">Bo Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2003.03756v4-abstract-short" style="display: inline;"> Single Image Super-Resolution (SISR) aims to improve resolution of small-size low-quality image from a single one. With popularity of consumer electronics in our daily life, this topic has become more and more attractive. In this paper, we argue that the curse of dimensionality is the underlying reason of limiting the performance of state-of-the-art algorithms. To address this issue, we propose Pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.03756v4-abstract-full').style.display = 'inline'; document.getElementById('2003.03756v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2003.03756v4-abstract-full" style="display: none;"> Single Image Super-Resolution (SISR) aims to improve resolution of small-size low-quality image from a single one. With popularity of consumer electronics in our daily life, this topic has become more and more attractive. In this paper, we argue that the curse of dimensionality is the underlying reason of limiting the performance of state-of-the-art algorithms. To address this issue, we propose Progressive Adversarial Network (PAN) that is capable of coping with this difficulty for domain-specific image super-resolution. The key principle of PAN is that we do not apply any distance-based reconstruction errors as the loss to be optimized, thus free from the restriction of the curse of dimensionality. To maintain faithful reconstruction precision, we resort to U-Net and progressive growing of neural architecture. The low-level features in encoder can be transferred into decoder to enhance textural details with U-Net. Progressive growing enhances image resolution gradually, thereby preserving precision of recovered image. Moreover, to obtain high-fidelity outputs, we leverage the framework of the powerful StyleGAN to perform adversarial learning. Without the curse of dimensionality, our model can super-resolve large-size images with remarkable photo-realistic details and few distortions. Extensive experiments demonstrate the superiority of our algorithm over state-of-the-arts both quantitatively and qualitatively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2003.03756v4-abstract-full').style.display = 'none'; document.getElementById('2003.03756v4-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, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 March, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2002.11977">arXiv:2002.11977</a> <span> [<a href="https://arxiv.org/pdf/2002.11977">pdf</a>, <a href="https://arxiv.org/format/2002.11977">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"> Multiple Discrimination and Pairwise CNN for View-based 3D Object Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gao%2C+Z">Z. Gao</a>, <a href="/search/eess?searchtype=author&query=Xue%2C+K+X">K. X Xue</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S+H">S. H Wan</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="2002.11977v1-abstract-short" style="display: inline;"> With the rapid development and wide application of computer, camera device, network and hardware technology, 3D object (or model) retrieval has attracted widespread attention and it has become a hot research topic in the computer vision domain. Deep learning features already available in 3D object retrieval have been proven to be better than the retrieval performance of hand-crafted features. Howe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.11977v1-abstract-full').style.display = 'inline'; document.getElementById('2002.11977v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2002.11977v1-abstract-full" style="display: none;"> With the rapid development and wide application of computer, camera device, network and hardware technology, 3D object (or model) retrieval has attracted widespread attention and it has become a hot research topic in the computer vision domain. Deep learning features already available in 3D object retrieval have been proven to be better than the retrieval performance of hand-crafted features. However, most existing networks do not take into account the impact of multi-view image selection on network training, and the use of contrastive loss alone only forcing the same-class samples to be as close as possible. In this work, a novel solution named Multi-view Discrimination and Pairwise CNN (MDPCNN) for 3D object retrieval is proposed to tackle these issues. It can simultaneously input of multiple batches and multiple views by adding the Slice layer and the Concat layer. Furthermore, a highly discriminative network is obtained by training samples that are not easy to be classified by clustering. Lastly, we deploy the contrastive-center loss and contrastive loss as the optimization objective that has better intra-class compactness and inter-class separability. Large-scale experiments show that the proposed MDPCNN can achieve a significant performance over the state-of-the-art algorithms in 3D object retrieval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2002.11977v1-abstract-full').style.display = 'none'; document.getElementById('2002.11977v1-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 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/2001.00150">arXiv:2001.00150</a> <span> [<a href="https://arxiv.org/pdf/2001.00150">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 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/10.1007/s11220-020-00281-8">10.1007/s11220-020-00281-8 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Total Variation Denoising Method Based on Median Filter and Phase Consistency </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huang%2C+S">Shuo Huang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Suiren Wan</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="2001.00150v1-abstract-short" style="display: inline;"> The total variation method is widely used in image noise suppression. However, this method is easy to cause the loss of image details, and it is also sensitive to parameters such as iteration time. In this work, the total variation method has been modified using a diffusion rate adjuster based on the phase congruency and a fusion filter of median filter and phase consistency boundary, which is cal… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.00150v1-abstract-full').style.display = 'inline'; document.getElementById('2001.00150v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2001.00150v1-abstract-full" style="display: none;"> The total variation method is widely used in image noise suppression. However, this method is easy to cause the loss of image details, and it is also sensitive to parameters such as iteration time. In this work, the total variation method has been modified using a diffusion rate adjuster based on the phase congruency and a fusion filter of median filter and phase consistency boundary, which is called the MPC-TV method. Experimental results indicate that MPC-TV method is effective in noise suppression, especially for the removing of speckle noise, and it can also improve the robustness of iteration time of TV method on noise with different variance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2001.00150v1-abstract-full').style.display = 'none'; document.getElementById('2001.00150v1-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 January, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Sens Imaging 21, 19 (2020) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1909.11953">arXiv:1909.11953</a> <span> [<a href="https://arxiv.org/pdf/1909.11953">pdf</a>, <a href="https://arxiv.org/format/1909.11953">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="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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wan%2C+S">Sheng Wan</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+C">Chen Gong</a>, <a href="/search/eess?searchtype=author&query=Zhong%2C+P">Ping Zhong</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+S">Shirui Pan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+G">Guangyu Li</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jian Yang</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="1909.11953v1-abstract-short" style="display: inline;"> In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.11953v1-abstract-full').style.display = 'inline'; document.getElementById('1909.11953v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1909.11953v1-abstract-full" style="display: none;"> In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed Graph Convolutional Network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2D image grids. Second, we refine the graph edge weight and the connective relationships among image regions by learning the improved adjacency matrix and the 'edge filter', so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in accurate region representations, and vice versa. The experiments carried out on three real-world benchmark datasets demonstrate that the proposed method yields significant improvement in the classification performance when compared with some state-of-the-art approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1909.11953v1-abstract-full').style.display = 'none'; document.getElementById('1909.11953v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.05023">arXiv:1906.05023</a> <span> [<a href="https://arxiv.org/pdf/1906.05023">pdf</a>, <a href="https://arxiv.org/format/1906.05023">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Towards Big data processing in IoT: Path Planning and Resource Management of UAV Base Stations in Mobile-Edge Computing System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuo Wan</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jiaxun Lu</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+P">Pingyi Fan</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="1906.05023v1-abstract-short" style="display: inline;"> Heavy data load and wide cover range have always been crucial problems for online data processing in internet of things (IoT). Recently, mobile-edge computing (MEC) and unmanned aerial vehicle base stations (UAV-BSs) have emerged as promising techniques in IoT. In this paper, we propose a three-layer online data processing network based on MEC technique. On the bottom layer, raw data are generated… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.05023v1-abstract-full').style.display = 'inline'; document.getElementById('1906.05023v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.05023v1-abstract-full" style="display: none;"> Heavy data load and wide cover range have always been crucial problems for online data processing in internet of things (IoT). Recently, mobile-edge computing (MEC) and unmanned aerial vehicle base stations (UAV-BSs) have emerged as promising techniques in IoT. In this paper, we propose a three-layer online data processing network based on MEC technique. On the bottom layer, raw data are generated by widely distributed sensors, which reflects local information. Upon them, unmanned aerial vehicle base stations (UAV-BSs) are deployed as moving MEC servers, which collect data and conduct initial steps of data processing. On top of them, a center cloud receives processed results and conducts further evaluation. As this is an online data processing system, the edge nodes should stabilize delay to ensure data freshness. Furthermore, limited onboard energy poses constraints to edge processing capability. To smartly manage network resources for saving energy and stabilizing delay, we develop an online determination policy based on Lyapunov Optimization. In cases of low data rate, it tends to reduce edge processor frequency for saving energy. In the presence of high data rate, it will smartly allocate bandwidth for edge data offloading. Meanwhile, hovering UAV-BSs bring a large and flexible service coverage, which results in the problem of effective path planning. In this paper, we apply deep reinforcement learning and develop an online path planning algorithm. Taking observations of around environment as input, a CNN network is trained to predict the reward of each action. By simulations, we validate its effectiveness in enhancing service coverage. The result will contribute to big data processing in future IoT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.05023v1-abstract-full').style.display = 'none'; document.getElementById('1906.05023v1-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 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.06133">arXiv:1905.06133</a> <span> [<a href="https://arxiv.org/pdf/1905.06133">pdf</a>, <a href="https://arxiv.org/format/1905.06133">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wan%2C+S">Sheng Wan</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+C">Chen Gong</a>, <a href="/search/eess?searchtype=author&query=Zhong%2C+P">Ping Zhong</a>, <a href="/search/eess?searchtype=author&query=Du%2C+B">Bo Du</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Lefei Zhang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jian Yang</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="1905.06133v1-abstract-short" style="display: inline;"> Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on regular square image regions with fixed size and weights, so they cannot universally adapt to the distinct local regions with various object distributions and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.06133v1-abstract-full').style.display = 'inline'; document.getElementById('1905.06133v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.06133v1-abstract-full" style="display: none;"> Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on regular square image regions with fixed size and weights, so they cannot universally adapt to the distinct local regions with various object distributions and geometric appearances. Therefore, their classification performances are still to be improved, especially in class boundaries. To alleviate this shortcoming, we consider employing the recently proposed Graph Convolutional Network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information. Different from the commonly used GCN models which work on a fixed graph, we enable the graph to be dynamically updated along with the graph convolution process, so that these two steps can be benefited from each other to gradually produce the discriminative embedded features as well as a refined graph. Moreover, to comprehensively deploy the multi-scale information inherited by hyperspectral images, we establish multiple input graphs with different neighborhood scales to extensively exploit the diversified spectral-spatial correlations at multiple scales. Therefore, our method is termed 'Multi-scale Dynamic Graph Convolutional Network' (MDGCN). The experimental results on three typical benchmark datasets firmly demonstrate the superiority of the proposed MDGCN to other state-of-the-art methods in both qualitative and quantitative aspects. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.06133v1-abstract-full').style.display = 'none'; document.getElementById('1905.06133v1-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> 14 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/1905.01663">arXiv:1905.01663</a> <span> [<a href="https://arxiv.org/pdf/1905.01663">pdf</a>, <a href="https://arxiv.org/format/1905.01663">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Towards Big data processing in IoT: network management for online edge data processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuo Wan</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jiaxun Lu</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+P">Pingyi Fan</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="1905.01663v1-abstract-short" style="display: inline;"> Heavy data load and wide cover range have always been crucial problems for internet of things (IoT). However, in mobile-edge computing (MEC) network, the huge data can be partly processed at the edge. In this paper, a MEC-based big data analysis network is discussed. The raw data generated by distributed network terminals are collected and processed by edge servers. The edge servers split out a la… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.01663v1-abstract-full').style.display = 'inline'; document.getElementById('1905.01663v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.01663v1-abstract-full" style="display: none;"> Heavy data load and wide cover range have always been crucial problems for internet of things (IoT). However, in mobile-edge computing (MEC) network, the huge data can be partly processed at the edge. In this paper, a MEC-based big data analysis network is discussed. The raw data generated by distributed network terminals are collected and processed by edge servers. The edge servers split out a large sum of redundant data and transmit extracted information to the center cloud for further analysis. However, for consideration of limited edge computation ability, part of the raw data in huge data sources may be directly transmitted to the cloud. To manage limited resources online, we propose an algorithm based on Lyapunov optimization to jointly optimize the policy of edge processor frequency, transmission power and bandwidth allocation. The algorithm aims at stabilizing data processing delay and saving energy without knowing probability distributions of data sources. The proposed network management algorithm may contribute to big data processing in future IoT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.01663v1-abstract-full').style.display = 'none'; document.getElementById('1905.01663v1-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 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/1901.10721">arXiv:1901.10721</a> <span> [<a href="https://arxiv.org/pdf/1901.10721">pdf</a>, <a href="https://arxiv.org/ps/1901.10721">ps</a>, <a href="https://arxiv.org/format/1901.10721">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</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/10.3390/e21020205">10.3390/e21020205 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Matching Users' Preference Under Target Revenue Constraints in Optimal Data Recommendation Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shanyun Liu</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+Y">Yunquan Dong</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+P">Pingyi Fan</a>, <a href="/search/eess?searchtype=author&query=She%2C+R">Rui She</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuo Wan</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="1901.10721v1-abstract-short" style="display: inline;"> This paper focuses on the problem of finding a particular data recommendation strategy based on the user preferences and a system expected revenue. To this end, we formulate this problem as an optimization by designing the recommendation mechanism as close to the user behavior as possible with a certain revenue constraint. In fact, the optimal recommendation distribution is the one that is the clo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.10721v1-abstract-full').style.display = 'inline'; document.getElementById('1901.10721v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1901.10721v1-abstract-full" style="display: none;"> This paper focuses on the problem of finding a particular data recommendation strategy based on the user preferences and a system expected revenue. To this end, we formulate this problem as an optimization by designing the recommendation mechanism as close to the user behavior as possible with a certain revenue constraint. In fact, the optimal recommendation distribution is the one that is the closest to the utility distribution in the sense of relative entropy and satisfies expected revenue. We show that the optimal recommendation distribution follows the same form as the message importance measure (MIM) if the target revenue is reasonable, i.e., neither too small nor too large. Therefore, the optimal recommendation distribution can be regarded as the normalized MIM, where the parameter, called importance coefficient, presents the concern of the system and switches the attention of the system over data sets with different occurring probability. By adjusting the importance coefficient, our MIM based framework of data recommendation can then be applied to system with various system requirements and data distributions.Therefore,the obtained results illustrate the physical meaning of MIM from the data recommendation perspective and validate the rationality of MIM in one aspect. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1901.10721v1-abstract-full').style.display = 'none'; document.getElementById('1901.10721v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 January, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">36 pages, 6 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/1807.05694">arXiv:1807.05694</a> <span> [<a href="https://arxiv.org/pdf/1807.05694">pdf</a>, <a href="https://arxiv.org/format/1807.05694">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Minor probability events detection in big data: An integrated approach with Bayesian testing and MIM </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wan%2C+S">Shuo Wan</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jiaxun Lu</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+P">Pingyi Fan</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="1807.05694v1-abstract-short" style="display: inline;"> The minor probability events detection is a crucial problem in Big data. Such events tend to include rarely occurring phenomenons which should be detected and monitored carefully. Given the prior probabilities of separate events and the conditional distributions of observations on the events, the Bayesian detection can be applied to estimate events behind the observations. It has been proved that… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.05694v1-abstract-full').style.display = 'inline'; document.getElementById('1807.05694v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1807.05694v1-abstract-full" style="display: none;"> The minor probability events detection is a crucial problem in Big data. Such events tend to include rarely occurring phenomenons which should be detected and monitored carefully. Given the prior probabilities of separate events and the conditional distributions of observations on the events, the Bayesian detection can be applied to estimate events behind the observations. It has been proved that Bayesian detection has the smallest overall testing error in average sense. However, when detecting an event with very small prior probability, the conditional Bayesian detection would result in high miss testing rate. To overcome such a problem, a modified detection approach is proposed based on Bayesian detection and message importance measure, which can reduce miss testing rate in conditions of detecting events with minor probability. The result can help to dig minor probability events in big data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.05694v1-abstract-full').style.display = 'none'; document.getElementById('1807.05694v1-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 July, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2018. </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