Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 52 results for author: <span class="mathjax">Shah, T</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/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Shah%2C+T">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="Shah, T"> </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=Shah%2C+T&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="Shah, T"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Shah%2C+T&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Shah%2C+T&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Shah%2C+T&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.17184">arXiv:2503.17184</a> <span> [<a href="https://arxiv.org/pdf/2503.17184">pdf</a>, <a href="https://arxiv.org/format/2503.17184">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </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/10.1016/j.inffus.2025.103087">10.1016/j.inffus.2025.103087 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Qiu%2C+X">Xueqi Qiu</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+X">Xingyu Miao</a>, <a href="/search/cs?searchtype=author&query=Wan%2C+F">Fan Wan</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Ojhab%2C+V">Varun Ojhab</a>, <a href="/search/cs?searchtype=author&query=Longa%2C+Y">Yang Longa</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</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="2503.17184v1-abstract-short" style="display: inline;"> Deepfake detection is crucial for curbing the harm it causes to society. However, current Deepfake detection methods fail to thoroughly explore artifact information across different domains due to insufficient intrinsic interactions. These interactions refer to the fusion and coordination after feature extraction processes across different domains, which are crucial for recognizing complex forgery… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17184v1-abstract-full').style.display = 'inline'; document.getElementById('2503.17184v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.17184v1-abstract-full" style="display: none;"> Deepfake detection is crucial for curbing the harm it causes to society. However, current Deepfake detection methods fail to thoroughly explore artifact information across different domains due to insufficient intrinsic interactions. These interactions refer to the fusion and coordination after feature extraction processes across different domains, which are crucial for recognizing complex forgery clues. Focusing on more generalized Deepfake detection, in this work, we introduce a novel bi-directional attention module to capture the local positional information of artifact clues from the spatial domain. This enables accurate artifact localization, thus addressing the coarse processing with artifact features. To further address the limitation that the proposed bi-directional attention module may not well capture global subtle forgery information in the artifact feature (e.g., textures or edges), we employ a fine-grained frequency attention module in the frequency domain. By doing so, we can obtain high-frequency information in the fine-grained features, which contains the global and subtle forgery information. Although these features from the diverse domains can be effectively and independently improved, fusing them directly does not effectively improve the detection performance. Therefore, we propose a feature superposition strategy that complements information from spatial and frequency domains. This strategy turns the feature components into the form of wave-like tokens, which are updated based on their phase, such that the distinctions between authentic and artifact features can be amplified. Our method demonstrates significant improvements over state-of-the-art (SOTA) methods on five public Deepfake datasets in capturing abnormalities across different manipulated operations and real-life. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.17184v1-abstract-full').style.display = 'none'; document.getElementById('2503.17184v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.15390">arXiv:2503.15390</a> <span> [<a href="https://arxiv.org/pdf/2503.15390">pdf</a>, <a href="https://arxiv.org/format/2503.15390">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"> FedSCA: Federated Tuning with Similarity-guided Collaborative Aggregation for Heterogeneous Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yumin Zhang</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yan Gao</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+H">Hanqing Guo</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+B">Bo Wei</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="2503.15390v1-abstract-short" style="display: inline;"> Transformer-based foundation models (FMs) have recently demonstrated remarkable performance in medical image segmentation. However, scaling these models is challenging due to the limited size of medical image datasets within isolated hospitals, where data centralization is restricted due to privacy concerns. These constraints, combined with the data-intensive nature of FMs, hinder their broader ap… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15390v1-abstract-full').style.display = 'inline'; document.getElementById('2503.15390v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.15390v1-abstract-full" style="display: none;"> Transformer-based foundation models (FMs) have recently demonstrated remarkable performance in medical image segmentation. However, scaling these models is challenging due to the limited size of medical image datasets within isolated hospitals, where data centralization is restricted due to privacy concerns. These constraints, combined with the data-intensive nature of FMs, hinder their broader application. Integrating federated learning (FL) with foundation models (FLFM) fine-tuning offers a potential solution to these challenges by enabling collaborative model training without data sharing, thus allowing FMs to take advantage of a diverse pool of sensitive medical image data across hospitals/clients. However, non-independent and identically distributed (non-IID) data among clients, paired with computational and communication constraints in federated environments, presents an additional challenge that limits further performance improvements and remains inadequately addressed in existing studies. In this work, we propose a novel FLFM fine-tuning framework, \underline{\textbf{Fed}}erated tuning with \underline{\textbf{S}}imilarity-guided \underline{\textbf{C}}ollaborative \underline{\textbf{A}}ggregation (FedSCA), encompassing all phases of the FL process. This includes (1) specially designed parameter-efficient fine-tuning (PEFT) for local client training to enhance computational efficiency; (2) partial low-level adapter transmission for communication efficiency; and (3) similarity-guided collaborative aggregation (SGCA) on the server side to address non-IID issues. Extensive experiments on three FL benchmarks for medical image segmentation demonstrate the effectiveness of our proposed FedSCA, establishing new SOTA performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.15390v1-abstract-full').style.display = 'none'; document.getElementById('2503.15390v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.13708">arXiv:2503.13708</a> <span> [<a href="https://arxiv.org/pdf/2503.13708">pdf</a>, <a href="https://arxiv.org/format/2503.13708">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> A Circular Construction Product Ontology for End-of-Life Decision-Making </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Adu-Duodu%2C+K">Kwabena Adu-Duodu</a>, <a href="/search/cs?searchtype=author&query=Wilson%2C+S">Stanly Wilson</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yinhao Li</a>, <a href="/search/cs?searchtype=author&query=Oladimeji%2C+A">Aanuoluwapo Oladimeji</a>, <a href="/search/cs?searchtype=author&query=Huraysi%2C+T">Talea Huraysi</a>, <a href="/search/cs?searchtype=author&query=Barati%2C+M">Masoud Barati</a>, <a href="/search/cs?searchtype=author&query=Perera%2C+C">Charith Perera</a>, <a href="/search/cs?searchtype=author&query=Solaiman%2C+E">Ellis Solaiman</a>, <a href="/search/cs?searchtype=author&query=Rana%2C+O">Omer Rana</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</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="2503.13708v1-abstract-short" style="display: inline;"> Efficient management of end-of-life (EoL) products is critical for advancing circularity in supply chains, particularly within the construction industry where EoL strategies are hindered by heterogenous lifecycle data and data silos. Current tools like Environmental Product Declarations (EPDs) and Digital Product Passports (DPPs) are limited by their dependency on seamless data integration and int… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13708v1-abstract-full').style.display = 'inline'; document.getElementById('2503.13708v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.13708v1-abstract-full" style="display: none;"> Efficient management of end-of-life (EoL) products is critical for advancing circularity in supply chains, particularly within the construction industry where EoL strategies are hindered by heterogenous lifecycle data and data silos. Current tools like Environmental Product Declarations (EPDs) and Digital Product Passports (DPPs) are limited by their dependency on seamless data integration and interoperability which remain significant challenges. To address these, we present the Circular Construction Product Ontology (CCPO), an applied framework designed to overcome semantic and data heterogeneity challenges in EoL decision-making for construction products. CCPO standardises vocabulary and facilitates data integration across supply chain stakeholders enabling lifecycle assessments (LCA) and robust decision-making. By aggregating disparate data into a unified product provenance, CCPO enables automated EoL recommendations through customisable SWRL rules aligned with European standards and stakeholder-specific circularity SLAs, demonstrating its scalability and integration capabilities. The adopted circular product scenario depicts CCPO's application while competency question evaluations show its superior performance in generating accurate EoL suggestions highlighting its potential to greatly improve decision-making in circular supply chains and its applicability in real-world construction environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.13708v1-abstract-full').style.display = 'none'; document.getElementById('2503.13708v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2503.02690">arXiv:2503.02690</a> <span> [<a href="https://arxiv.org/pdf/2503.02690">pdf</a>, <a href="https://arxiv.org/format/2503.02690">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</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="Atmospheric and Oceanic Physics">physics.ao-ph</span> </div> </div> <p class="title is-5 mathjax"> Generative Modeling of Microweather Wind Velocities for Urban Air Mobility </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T+A">Tristan A. Shah</a>, <a href="/search/cs?searchtype=author&query=Stanley%2C+M+C">Michael C. Stanley</a>, <a href="/search/cs?searchtype=author&query=Warner%2C+J+E">James E. Warner</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="2503.02690v1-abstract-short" style="display: inline;"> Motivated by the pursuit of safe, reliable, and weather-tolerant urban air mobility (UAM) solutions, this work proposes a generative modeling approach for characterizing microweather wind velocities. Microweather, or the weather conditions in highly localized areas, is particularly complex in urban environments owing to the chaotic and turbulent nature of wind flows. Furthermore, traditional means… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02690v1-abstract-full').style.display = 'inline'; document.getElementById('2503.02690v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2503.02690v1-abstract-full" style="display: none;"> Motivated by the pursuit of safe, reliable, and weather-tolerant urban air mobility (UAM) solutions, this work proposes a generative modeling approach for characterizing microweather wind velocities. Microweather, or the weather conditions in highly localized areas, is particularly complex in urban environments owing to the chaotic and turbulent nature of wind flows. Furthermore, traditional means of assessing local wind fields are not generally viable solutions for UAM applications: 1) field measurements that would rely on permanent wind profiling systems in operational air space are not practical, 2) physics-based models that simulate fluid dynamics at a sufficiently high resolution are not computationally tractable, and 3) data-driven modeling approaches that are largely deterministic ignore the inherent variability in turbulent flows that dictates UAM reliability. Thus, advancements in predictive capabilities are needed to help mitigate the unique operational safety risks that microweather winds pose for smaller, lighter weight UAM aircraft. This work aims to model microweather wind velocities in a manner that is computationally-efficient, captures random variability, and would only require a temporary, rather than permanent, field measurement campaign. Inspired by recent breakthroughs in conditional generative AI such as text-to-image generation, the proposed approach learns a probabilistic macro-to-microweather mapping between regional weather forecasts and measured local wind velocities using generative modeling (denoising diffusion probabilistic models, flow matching, and Gaussian mixture models). A simple proof of concept was implemented using a dataset comprised of local (micro) measurements from a Sonic Detection and Ranging (SoDAR) wind profiler along with (macro) forecast data from a nearby weather station over the same time period. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2503.02690v1-abstract-full').style.display = 'none'; document.getElementById('2503.02690v1-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 March, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 pages, 13 figures, published in 2025 IEEE Aerospace Conference proceedings</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.08784">arXiv:2502.08784</a> <span> [<a href="https://arxiv.org/pdf/2502.08784">pdf</a>, <a href="https://arxiv.org/format/2502.08784">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Acoustic Wave Manipulation Through Sparse Robotic Actuation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tristan Shah</a>, <a href="/search/cs?searchtype=author&query=Smilovich%2C+N">Noam Smilovich</a>, <a href="/search/cs?searchtype=author&query=Amirkulova%2C+F">Feruza Amirkulova</a>, <a href="/search/cs?searchtype=author&query=Gerges%2C+S">Samer Gerges</a>, <a href="/search/cs?searchtype=author&query=Tiomkin%2C+S">Stas Tiomkin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.08784v2-abstract-short" style="display: inline;"> Recent advancements in robotics, control, and machine learning have facilitated progress in the challenging area of object manipulation. These advancements include, among others, the use of deep neural networks to represent dynamics that are partially observed by robot sensors, as well as effective control using sparse control signals. In this work, we explore a more general problem: the manipulat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08784v2-abstract-full').style.display = 'inline'; document.getElementById('2502.08784v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.08784v2-abstract-full" style="display: none;"> Recent advancements in robotics, control, and machine learning have facilitated progress in the challenging area of object manipulation. These advancements include, among others, the use of deep neural networks to represent dynamics that are partially observed by robot sensors, as well as effective control using sparse control signals. In this work, we explore a more general problem: the manipulation of acoustic waves, which are partially observed by a robot capable of influencing the waves through spatially sparse actuators. This problem holds great potential for the design of new artificial materials, ultrasonic cutting tools, energy harvesting, and other applications. We develop an efficient data-driven method for robot learning that is applicable to either focusing scattered acoustic energy in a designated region or suppressing it, depending on the desired task. The proposed method is better in terms of a solution quality and computational complexity as compared to a state-of-the-art learning based method for manipulation of dynamical systems governed by partial differential equations. Furthermore our proposed method is competitive with a classical semi-analytical method in acoustics research on the demonstrated tasks. We have made the project code publicly available, along with a web page featuring video demonstrations: https://gladisor.github.io/waves/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.08784v2-abstract-full').style.display = 'none'; document.getElementById('2502.08784v2-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICRA 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.19084">arXiv:2501.19084</a> <span> [<a href="https://arxiv.org/pdf/2501.19084">pdf</a>, <a href="https://arxiv.org/format/2501.19084">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> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TPAMI.2025.3535916">10.1109/TPAMI.2025.3535916 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miao%2C+X">Xingyu Miao</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Bai%2C+Y">Yang Bai</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Song%2C+J">Jun Song</a>, <a href="/search/cs?searchtype=author&query=Long%2C+Y">Yang Long</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+L">Ling Shao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.19084v1-abstract-short" style="display: inline;"> In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed and storage requirements, our approach aims to streamline the workflow by directly and effectively distilling dense CLIP features, thereby achieving precise segme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.19084v1-abstract-full').style.display = 'inline'; document.getElementById('2501.19084v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.19084v1-abstract-full" style="display: none;"> In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed and storage requirements, our approach aims to streamline the workflow by directly and effectively distilling dense CLIP features, thereby achieving precise segmentation of 3D scenes using text. To achieve this, we introduce an adapter module and mitigate the noise issue in the dense CLIP feature distillation process through a self-cross-training strategy. Moreover, to enhance the accuracy of segmentation edges, this work presents a low-rank transient query attention mechanism. To ensure the consistency of segmentation for similar colors under different viewpoints, we convert the segmentation task into a classification task through label volume, which significantly improves the consistency of segmentation in color-similar areas. We also propose a simplified text augmentation strategy to alleviate the issue of ambiguity in the correspondence between CLIP features and text. Extensive experimental results show that our method surpasses current state-of-the-art technologies in both training speed and performance. Our code is available on: https://github.com/xingy038/Laser.git. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.19084v1-abstract-full').style.display = 'none'; document.getElementById('2501.19084v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.14249">arXiv:2501.14249</a> <span> [<a href="https://arxiv.org/pdf/2501.14249">pdf</a>, <a href="https://arxiv.org/format/2501.14249">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Humanity's Last Exam </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Phan%2C+L">Long Phan</a>, <a href="/search/cs?searchtype=author&query=Gatti%2C+A">Alice Gatti</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Z">Ziwen Han</a>, <a href="/search/cs?searchtype=author&query=Li%2C+N">Nathaniel Li</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+J">Josephina Hu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Hugh Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C+B+C">Chen Bo Calvin Zhang</a>, <a href="/search/cs?searchtype=author&query=Shaaban%2C+M">Mohamed Shaaban</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+J">John Ling</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+S">Sean Shi</a>, <a href="/search/cs?searchtype=author&query=Choi%2C+M">Michael Choi</a>, <a href="/search/cs?searchtype=author&query=Agrawal%2C+A">Anish Agrawal</a>, <a href="/search/cs?searchtype=author&query=Chopra%2C+A">Arnav Chopra</a>, <a href="/search/cs?searchtype=author&query=Khoja%2C+A">Adam Khoja</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+R">Ryan Kim</a>, <a href="/search/cs?searchtype=author&query=Ren%2C+R">Richard Ren</a>, <a href="/search/cs?searchtype=author&query=Hausenloy%2C+J">Jason Hausenloy</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+O">Oliver Zhang</a>, <a href="/search/cs?searchtype=author&query=Mazeika%2C+M">Mantas Mazeika</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Tung Nguyen</a>, <a href="/search/cs?searchtype=author&query=Anderson%2C+D">Daron Anderson</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+I+A">Imad Ali Shah</a>, <a href="/search/cs?searchtype=author&query=Doroshenko%2C+M">Mikhail Doroshenko</a>, <a href="/search/cs?searchtype=author&query=Stokes%2C+A+C">Alun Cennyth Stokes</a>, <a href="/search/cs?searchtype=author&query=Mahmood%2C+M">Mobeen Mahmood</a> , et al. (709 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.14249v5-abstract-short" style="display: inline;"> Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14249v5-abstract-full').style.display = 'inline'; document.getElementById('2501.14249v5-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.14249v5-abstract-full" style="display: none;"> Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,700 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.14249v5-abstract-full').style.display = 'none'; document.getElementById('2501.14249v5-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">27 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/2412.18926">arXiv:2412.18926</a> <span> [<a href="https://arxiv.org/pdf/2412.18926">pdf</a>, <a href="https://arxiv.org/format/2412.18926">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Exemplar-condensed Federated Class-incremental Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+R">Rui Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yumin Zhang</a>, <a href="/search/cs?searchtype=author&query=Ojha%2C+V">Varun Ojha</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+B">Bo Wei</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.18926v1-abstract-short" style="display: inline;"> We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exemplars. The proposed method eliminates the limitations of exemplar selection in replay-based approaches for mitigating catastrophic forgetting in federated continual learning (FCL). The limitations particularly related t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18926v1-abstract-full').style.display = 'inline'; document.getElementById('2412.18926v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.18926v1-abstract-full" style="display: none;"> We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exemplars. The proposed method eliminates the limitations of exemplar selection in replay-based approaches for mitigating catastrophic forgetting in federated continual learning (FCL). The limitations particularly related to the heterogeneity of information density of each summarized data. Our approach maintains the consistency of training gradients and the relationship to past tasks for the summarized exemplars to represent the streaming data compared to the original images effectively. Additionally, our approach reduces the information-level heterogeneity of the summarized data by inter-client sharing of the disentanglement generative model. Extensive experiments show that our ECoral outperforms several state-of-the-art methods and can be seamlessly integrated with many existing approaches to enhance performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18926v1-abstract-full').style.display = 'none'; document.getElementById('2412.18926v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00441">arXiv:2412.00441</a> <span> [<a href="https://arxiv.org/pdf/2412.00441">pdf</a>, <a href="https://arxiv.org/format/2412.00441">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Fine Grained Analysis and Optimization of Large Scale Automotive Radar Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+M+T">Mohammad Taha Shah</a>, <a href="/search/cs?searchtype=author&query=Ghatak%2C+G">Gourab Ghatak</a>, <a href="/search/cs?searchtype=author&query=Ram%2C+S+S">Shobha Sundar Ram</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.00441v1-abstract-short" style="display: inline;"> Advanced driver assistance systems (ADAS) enabled by automotive radars have significantly enhanced vehicle safety and driver experience. However, the extensive use of radars in dense road conditions introduces mutual interference, which degrades detection accuracy and reliability. Traditional interference models are limited to simple highway scenarios and cannot characterize the performance of aut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00441v1-abstract-full').style.display = 'inline'; document.getElementById('2412.00441v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00441v1-abstract-full" style="display: none;"> Advanced driver assistance systems (ADAS) enabled by automotive radars have significantly enhanced vehicle safety and driver experience. However, the extensive use of radars in dense road conditions introduces mutual interference, which degrades detection accuracy and reliability. Traditional interference models are limited to simple highway scenarios and cannot characterize the performance of automotive radars in dense urban environments. In our prior work, we employed stochastic geometry (SG) to develop two automotive radar network models: the Poisson line Cox process (PLCP) for dense city centers and smaller urban zones and the binomial line Cox process (BLCP) to encompass both urban cores and suburban areas. In this work, we introduce the meta-distribution (MD) framework upon these two models to distinguish the sources of variability in radar detection metrics. Additionally, we optimize the radar beamwidth and transmission probability to maximize the number of successful detections of a radar node in the network. Further, we employ a computationally efficient Chebyshev-Markov (CM) bound method for reconstructing MDs, achieving higher accuracy than the conventional Gil-Pelaez theorem. Using the framework, we analyze the specific impacts of beamwidth, detection range, and interference on radar detection performance and offer practical insights for developing adaptive radar systems tailored to diverse traffic and environmental conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00441v1-abstract-full').style.display = 'none'; document.getElementById('2412.00441v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE TSP</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.12189">arXiv:2410.12189</a> <span> [<a href="https://arxiv.org/pdf/2410.12189">pdf</a>, <a href="https://arxiv.org/format/2410.12189">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shankar%2C+S">Shreya Shankar</a>, <a href="/search/cs?searchtype=author&query=Chambers%2C+T">Tristan Chambers</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tarak Shah</a>, <a href="/search/cs?searchtype=author&query=Parameswaran%2C+A+G">Aditya G. Parameswaran</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+E">Eugene Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.12189v2-abstract-short" style="display: inline;"> Analyzing unstructured data has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered processing of unstructured data. However, these frameworks focus on reducing cost when executing user-specified operations using LLMs, rather than improving accuracy, executing most ope… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12189v2-abstract-full').style.display = 'inline'; document.getElementById('2410.12189v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.12189v2-abstract-full" style="display: none;"> Analyzing unstructured data has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered processing of unstructured data. However, these frameworks focus on reducing cost when executing user-specified operations using LLMs, rather than improving accuracy, executing most operations as-is (in a single LLM call). This is problematic for complex tasks and data, where LLM outputs for user-defined operations are often inaccurate, even with optimized prompts. For example, an LLM may struggle to identify {\em all} instances of specific clauses, like force majeure or indemnification, in lengthy legal documents, requiring decomposition of the data, the task, or both. We present DocETL, a system that optimizes complex document processing pipelines, while accounting for LLM shortcomings. DocETL offers a declarative interface for users to define such pipelines and uses an agent-based approach to automatically optimize them, leveraging novel agent-based rewrites (that we call rewrite directives), as well as an optimization and evaluation framework. We introduce (i) logical rewriting of pipelines, tailored for LLM-based tasks, (ii) an agent-guided plan evaluation mechanism that synthesizes and orchestrates task-specific validation prompts, and (iii) an optimization algorithm that efficiently finds promising plans, considering the latencies of agent-based plan generation and evaluation. Our evaluation on four different unstructured document analysis tasks demonstrates that DocETL finds plans with outputs that are 25 to 80% more accurate than well-engineered baselines, addressing a critical gap in unstructured data analysis. DocETL is open-source at docetl.org, and as of November 2024, has amassed over 1.3k GitHub Stars, with users spanning a variety of domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.12189v2-abstract-full').style.display = 'none'; document.getElementById('2410.12189v2-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">20 pages, 5 figures, 6 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03487">arXiv:2410.03487</a> <span> [<a href="https://arxiv.org/pdf/2410.03487">pdf</a>, <a href="https://arxiv.org/format/2410.03487">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</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/10.53555/jes.v20i10s.6126">10.53555/jes.v20i10s.6126 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Multimodal Framework for Deepfake Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gandhi%2C+K">Kashish Gandhi</a>, <a href="/search/cs?searchtype=author&query=Kulkarni%2C+P">Prutha Kulkarni</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Taran Shah</a>, <a href="/search/cs?searchtype=author&query=Chaudhari%2C+P">Piyush Chaudhari</a>, <a href="/search/cs?searchtype=author&query=Narvekar%2C+M">Meera Narvekar</a>, <a href="/search/cs?searchtype=author&query=Ghag%2C+K">Kranti Ghag</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.03487v1-abstract-short" style="display: inline;"> The rapid advancement of deepfake technology poses a significant threat to digital media integrity. Deepfakes, synthetic media created using AI, can convincingly alter videos and audio to misrepresent reality. This creates risks of misinformation, fraud, and severe implications for personal privacy and security. Our research addresses the critical issue of deepfakes through an innovative multimoda… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03487v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03487v1-abstract-full" style="display: none;"> The rapid advancement of deepfake technology poses a significant threat to digital media integrity. Deepfakes, synthetic media created using AI, can convincingly alter videos and audio to misrepresent reality. This creates risks of misinformation, fraud, and severe implications for personal privacy and security. Our research addresses the critical issue of deepfakes through an innovative multimodal approach, targeting both visual and auditory elements. This comprehensive strategy recognizes that human perception integrates multiple sensory inputs, particularly visual and auditory information, to form a complete understanding of media content. For visual analysis, a model that employs advanced feature extraction techniques was developed, extracting nine distinct facial characteristics and then applying various machine learning and deep learning models. For auditory analysis, our model leverages mel-spectrogram analysis for feature extraction and then applies various machine learning and deep learningmodels. To achieve a combined analysis, real and deepfake audio in the original dataset were swapped for testing purposes and ensured balanced samples. Using our proposed models for video and audio classification i.e. Artificial Neural Network and VGG19, the overall sample is classified as deepfake if either component is identified as such. Our multimodal framework combines visual and auditory analyses, yielding an accuracy of 94%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03487v1-abstract-full').style.display = 'none'; document.getElementById('2410.03487v1-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">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 pages, 14 figures, Accepted in Journal of Electrical Systems</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00630">arXiv:2410.00630</a> <span> [<a href="https://arxiv.org/pdf/2410.00630">pdf</a>, <a href="https://arxiv.org/format/2410.00630">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3680528.3687580">10.1145/3680528.3687580 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=B%C3%BChler%2C+M+C">Marcel C. B眉hler</a>, <a href="/search/cs?searchtype=author&query=Li%2C+G">Gengyan Li</a>, <a href="/search/cs?searchtype=author&query=Wood%2C+E">Erroll Wood</a>, <a href="/search/cs?searchtype=author&query=Helminger%2C+L">Leonhard Helminger</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xu Chen</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tanmay Shah</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Daoye Wang</a>, <a href="/search/cs?searchtype=author&query=Garbin%2C+S">Stephan Garbin</a>, <a href="/search/cs?searchtype=author&query=Orts-Escolano%2C+S">Sergio Orts-Escolano</a>, <a href="/search/cs?searchtype=author&query=Hilliges%2C+O">Otmar Hilliges</a>, <a href="/search/cs?searchtype=author&query=Lagun%2C+D">Dmitry Lagun</a>, <a href="/search/cs?searchtype=author&query=Riviere%2C+J">J茅r茅my Riviere</a>, <a href="/search/cs?searchtype=author&query=Gotardo%2C+P">Paulo Gotardo</a>, <a href="/search/cs?searchtype=author&query=Beeler%2C+T">Thabo Beeler</a>, <a href="/search/cs?searchtype=author&query=Meka%2C+A">Abhimitra Meka</a>, <a href="/search/cs?searchtype=author&query=Sarkar%2C+K">Kripasindhu Sarkar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.00630v1-abstract-short" style="display: inline;"> Volumetric modeling and neural radiance field representations have revolutionized 3D face capture and photorealistic novel view synthesis. However, these methods often require hundreds of multi-view input images and are thus inapplicable to cases with less than a handful of inputs. We present a novel volumetric prior on human faces that allows for high-fidelity expressive face modeling from as few… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00630v1-abstract-full').style.display = 'inline'; document.getElementById('2410.00630v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00630v1-abstract-full" style="display: none;"> Volumetric modeling and neural radiance field representations have revolutionized 3D face capture and photorealistic novel view synthesis. However, these methods often require hundreds of multi-view input images and are thus inapplicable to cases with less than a handful of inputs. We present a novel volumetric prior on human faces that allows for high-fidelity expressive face modeling from as few as three input views captured in the wild. Our key insight is that an implicit prior trained on synthetic data alone can generalize to extremely challenging real-world identities and expressions and render novel views with fine idiosyncratic details like wrinkles and eyelashes. We leverage a 3D Morphable Face Model to synthesize a large training set, rendering each identity with different expressions, hair, clothing, and other assets. We then train a conditional Neural Radiance Field prior on this synthetic dataset and, at inference time, fine-tune the model on a very sparse set of real images of a single subject. On average, the fine-tuning requires only three inputs to cross the synthetic-to-real domain gap. The resulting personalized 3D model reconstructs strong idiosyncratic facial expressions and outperforms the state-of-the-art in high-quality novel view synthesis of faces from sparse inputs in terms of perceptual and photo-metric quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00630v1-abstract-full').style.display = 'none'; document.getElementById('2410.00630v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Siggraph Asia Conference Papers 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17517">arXiv:2409.17517</a> <span> [<a href="https://arxiv.org/pdf/2409.17517">pdf</a>, <a href="https://arxiv.org/format/2409.17517">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Dataset Distillation-based Hybrid Federated Learning on Non-IID Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shi%2C+X">Xiufang Shi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wei Zhang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+M">Mincheng Wu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+G">Guangyi Liu</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+Z">Zhenyu Wen</a>, <a href="/search/cs?searchtype=author&query=He%2C+S">Shibo He</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17517v1-abstract-short" style="display: inline;"> In federated learning, the heterogeneity of client data has a great impact on the performance of model training. Many heterogeneity issues in this process are raised by non-independently and identically distributed (Non-IID) data. This study focuses on the issue of label distribution skew. To address it, we propose a hybrid federated learning framework called HFLDD, which integrates dataset distil… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17517v1-abstract-full').style.display = 'inline'; document.getElementById('2409.17517v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17517v1-abstract-full" style="display: none;"> In federated learning, the heterogeneity of client data has a great impact on the performance of model training. Many heterogeneity issues in this process are raised by non-independently and identically distributed (Non-IID) data. This study focuses on the issue of label distribution skew. To address it, we propose a hybrid federated learning framework called HFLDD, which integrates dataset distillation to generate approximately independent and equally distributed (IID) data, thereby improving the performance of model training. Particularly, we partition the clients into heterogeneous clusters, where the data labels among different clients within a cluster are unbalanced while the data labels among different clusters are balanced. The cluster headers collect distilled data from the corresponding cluster members, and conduct model training in collaboration with the server. This training process is like traditional federated learning on IID data, and hence effectively alleviates the impact of Non-IID data on model training. Furthermore, we compare our proposed method with typical baseline methods on public datasets. Experimental results demonstrate that when the data labels are severely imbalanced, the proposed HFLDD outperforms the baseline methods in terms of both test accuracy and communication cost. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17517v1-abstract-full').style.display = 'none'; document.getElementById('2409.17517v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.05553">arXiv:2409.05553</a> <span> [<a href="https://arxiv.org/pdf/2409.05553">pdf</a>, <a href="https://arxiv.org/format/2409.05553">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="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Towards Resilient 6G O-RAN: An Energy-Efficient URLLC Resource Allocation Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sohaib%2C+R+M">Rana M. Sohaib</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+S+T">Syed Tariq Shah</a>, <a href="/search/cs?searchtype=author&query=Yadav%2C+P">Poonam Yadav</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.05553v1-abstract-short" style="display: inline;"> The demands of ultra-reliable low-latency communication (URLLC) in ``NextG" cellular networks necessitate innovative approaches for efficient resource utilisation. The current literature on 6G O-RAN primarily addresses improved mobile broadband (eMBB) performance or URLLC latency optimisation individually, often neglecting the intricate balance required to optimise both simultaneously under practi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05553v1-abstract-full').style.display = 'inline'; document.getElementById('2409.05553v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.05553v1-abstract-full" style="display: none;"> The demands of ultra-reliable low-latency communication (URLLC) in ``NextG" cellular networks necessitate innovative approaches for efficient resource utilisation. The current literature on 6G O-RAN primarily addresses improved mobile broadband (eMBB) performance or URLLC latency optimisation individually, often neglecting the intricate balance required to optimise both simultaneously under practical constraints. This paper addresses this gap by proposing a DRL-based resource allocation framework integrated with meta-learning to manage eMBB and URLLC services adaptively. Our approach efficiently allocates heterogeneous network resources, aiming to maximise energy efficiency (EE) while minimising URLLC latency, even under varying environmental conditions. We highlight the critical importance of accurately estimating the traffic distribution flow in the multi-connectivity (MC) scenario, as its uncertainty can significantly degrade EE. The proposed framework demonstrates superior adaptability across different path loss models, outperforming traditional methods and paving the way for more resilient and efficient 6G networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.05553v1-abstract-full').style.display = 'none'; document.getElementById('2409.05553v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This manuscript is being submitted for peer review and potential publication in the IEEE Open Journal of the Communications Society</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.15084">arXiv:2408.15084</a> <span> [<a href="https://arxiv.org/pdf/2408.15084">pdf</a>, <a href="https://arxiv.org/format/2408.15084">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> CR-Enabled NOMA Integrated Non-Terrestrial IoT Networks with Transmissive RIS </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khan%2C+W+U">Wali Ullah Khan</a>, <a href="/search/cs?searchtype=author&query=Ali%2C+Z">Zain Ali</a>, <a href="/search/cs?searchtype=author&query=Mahmood%2C+A">Asad Mahmood</a>, <a href="/search/cs?searchtype=author&query=Lagunas%2C+E">Eva Lagunas</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+S+T">Syed Tariq Shah</a>, <a href="/search/cs?searchtype=author&query=Chatzinotas%2C+S">Symeon Chatzinotas</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="2408.15084v1-abstract-short" style="display: inline;"> This work proposes a T-RIS-equipped LEO satellite communication in cognitive radio-enabled integrated NTNs. In the proposed system, a GEO satellite operates as a primary network, and a T-RIS-equipped LEO satellite operates as a secondary IoT network. The objective is to maximize the sum rate of T-RIS-equipped LEO satellite communication using downlink NOMA while ensuring the service quality of GEO… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15084v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15084v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15084v1-abstract-full" style="display: none;"> This work proposes a T-RIS-equipped LEO satellite communication in cognitive radio-enabled integrated NTNs. In the proposed system, a GEO satellite operates as a primary network, and a T-RIS-equipped LEO satellite operates as a secondary IoT network. The objective is to maximize the sum rate of T-RIS-equipped LEO satellite communication using downlink NOMA while ensuring the service quality of GEO cellular users. Our framework simultaneously optimizes the total transmit power of LEO, NOMA power allocation for LEO IoT (LIoT) and T-RIS phase shift design subject to the service quality of LIoT and interference temperature to the primary GEO network. To solve the non-convex sum rate maximization problem, we first adopt successive convex approximations to reduce the complexity of the formulated optimization. Then, we divide the problem into two parts, i.e., power allocation of LEO and phase shift design of T-RIS. The power allocation problem is solved using KKT conditions, while the phase shift problem is handled by Taylor approximation and semidefinite programming. Numerical results are provided to validate the proposed optimization framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15084v1-abstract-full').style.display = 'none'; document.getElementById('2408.15084v1-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">7,5</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13645">arXiv:2408.13645</a> <span> [<a href="https://arxiv.org/pdf/2408.13645">pdf</a>, <a href="https://arxiv.org/format/2408.13645">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> </div> </div> <p class="title is-5 mathjax"> Modeling and Statistical Characterization of Large-Scale Automotive Radar Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+M+T">Mohammad Taha Shah</a>, <a href="/search/cs?searchtype=author&query=Ghatak%2C+G">Gourab Ghatak</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+A">Ankit Kumar</a>, <a href="/search/cs?searchtype=author&query=Ram%2C+S+S">Shobha Sundar Ram</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="2408.13645v2-abstract-short" style="display: inline;"> The impact of discrete clutter and co-channel interference on the performance of automotive radar networks has been studied using stochastic geometry, in particular, by leveraging two-dimensional Poisson point processes (PPPs). However, such characterization does not take into account the impact of street geometry and the fact that the location of the automotive radars are restricted to the street… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13645v2-abstract-full').style.display = 'inline'; document.getElementById('2408.13645v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13645v2-abstract-full" style="display: none;"> The impact of discrete clutter and co-channel interference on the performance of automotive radar networks has been studied using stochastic geometry, in particular, by leveraging two-dimensional Poisson point processes (PPPs). However, such characterization does not take into account the impact of street geometry and the fact that the location of the automotive radars are restricted to the streets as their domain rather than the entire Euclidean plane. In addition, the structure of the streets may change drastically as a vehicle moves out of a city center towards the outskirts. Consequently, not only the radar performance change but also the radar parameters and protocols must be adapted for optimum performance. In this paper, we propose and characterize line and Cox process-based street and point models to analyze large-scale automotive radar networks. We consider the classical Poisson line process (PLP) and the newly introduced Binomial line process (BLP) model to emulate the streets and the corresponding PPP-based Cox process to emulate the vehicular nodes. In particular, the BLP model effectively considers the spatial variation of street geometry across different parts of the city. We derive the effective interference set experienced by an automotive radar, the statistics of distance to interferers, and characterize the detection probability of the ego radar as a function of street and vehicle density. Finally, leveraging the real-world data on urban streets and vehicle density across different cities of the world, we present how the radar performance varies in different parts of the city as well as across different times of the day. Thus, our study equips network operators and automotive manufacturers with essential system design insights to plan and optimize automotive radar networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13645v2-abstract-full').style.display = 'none'; document.getElementById('2408.13645v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE TWC</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.07009">arXiv:2408.07009</a> <span> [<a href="https://arxiv.org/pdf/2408.07009">pdf</a>, <a href="https://arxiv.org/format/2408.07009">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> </div> </div> <p class="title is-5 mathjax"> Imagen 3 </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Imagen-Team-Google"> Imagen-Team-Google</a>, <a href="/search/cs?searchtype=author&query=%3A"> :</a>, <a href="/search/cs?searchtype=author&query=Baldridge%2C+J">Jason Baldridge</a>, <a href="/search/cs?searchtype=author&query=Bauer%2C+J">Jakob Bauer</a>, <a href="/search/cs?searchtype=author&query=Bhutani%2C+M">Mukul Bhutani</a>, <a href="/search/cs?searchtype=author&query=Brichtova%2C+N">Nicole Brichtova</a>, <a href="/search/cs?searchtype=author&query=Bunner%2C+A">Andrew Bunner</a>, <a href="/search/cs?searchtype=author&query=Castrejon%2C+L">Lluis Castrejon</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+K">Kelvin Chan</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yichang Chen</a>, <a href="/search/cs?searchtype=author&query=Dieleman%2C+S">Sander Dieleman</a>, <a href="/search/cs?searchtype=author&query=Du%2C+Y">Yuqing Du</a>, <a href="/search/cs?searchtype=author&query=Eaton-Rosen%2C+Z">Zach Eaton-Rosen</a>, <a href="/search/cs?searchtype=author&query=Fei%2C+H">Hongliang Fei</a>, <a href="/search/cs?searchtype=author&query=de+Freitas%2C+N">Nando de Freitas</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+Y">Yilin Gao</a>, <a href="/search/cs?searchtype=author&query=Gladchenko%2C+E">Evgeny Gladchenko</a>, <a href="/search/cs?searchtype=author&query=Colmenarejo%2C+S+G">Sergio G贸mez Colmenarejo</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+M">Mandy Guo</a>, <a href="/search/cs?searchtype=author&query=Haig%2C+A">Alex Haig</a>, <a href="/search/cs?searchtype=author&query=Hawkins%2C+W">Will Hawkins</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Hexiang Hu</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+H">Huilian Huang</a>, <a href="/search/cs?searchtype=author&query=Igwe%2C+T+P">Tobenna Peter Igwe</a>, <a href="/search/cs?searchtype=author&query=Kaplanis%2C+C">Christos Kaplanis</a> , et al. (237 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.07009v3-abstract-short" style="display: inline;"> We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred over other state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss issues around safety and representation, as well as methods we used to minimize the potential harm of our models. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.07009v3-abstract-full" style="display: none;"> We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred over other state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss issues around safety and representation, as well as methods we used to minimize the potential harm of our models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.07009v3-abstract-full').style.display = 'none'; document.getElementById('2408.07009v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.15914">arXiv:2405.15914</a> <span> [<a href="https://arxiv.org/pdf/2405.15914">pdf</a>, <a href="https://arxiv.org/format/2405.15914">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> </div> </div> <p class="title is-5 mathjax"> ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score Matching </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yumin Zhang</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+X">Xingyu Miao</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+B">Bo Wei</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Long%2C+Y">Yang Long</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</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="2405.15914v1-abstract-short" style="display: inline;"> Text-to-3D content creation is a rapidly evolving research area. Given the scarcity of 3D data, current approaches often adapt pre-trained 2D diffusion models for 3D synthesis. Among these approaches, Score Distillation Sampling (SDS) has been widely adopted. However, the issue of over-smoothing poses a significant limitation on the high-fidelity generation of 3D models. To address this challenge,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15914v1-abstract-full').style.display = 'inline'; document.getElementById('2405.15914v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15914v1-abstract-full" style="display: none;"> Text-to-3D content creation is a rapidly evolving research area. Given the scarcity of 3D data, current approaches often adapt pre-trained 2D diffusion models for 3D synthesis. Among these approaches, Score Distillation Sampling (SDS) has been widely adopted. However, the issue of over-smoothing poses a significant limitation on the high-fidelity generation of 3D models. To address this challenge, LucidDreamer replaces the Denoising Diffusion Probabilistic Model (DDPM) in SDS with the Denoising Diffusion Implicit Model (DDIM) to construct Interval Score Matching (ISM). However, ISM inevitably inherits inconsistencies from DDIM, causing reconstruction errors during the DDIM inversion process. This results in poor performance in the detailed generation of 3D objects and loss of content. To alleviate these problems, we propose a novel method named Exact Score Matching (ESM). Specifically, ESM leverages auxiliary variables to mathematically guarantee exact recovery in the DDIM reverse process. Furthermore, to effectively capture the dynamic changes of the original and auxiliary variables, the LoRA of a pre-trained diffusion model implements these exact paths. Extensive experiments demonstrate the effectiveness of ESM in text-to-3D generation, particularly highlighting its superiority in detailed generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15914v1-abstract-full').style.display = 'none'; document.getElementById('2405.15914v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.13900">arXiv:2405.13900</a> <span> [<a href="https://arxiv.org/pdf/2405.13900">pdf</a>, <a href="https://arxiv.org/format/2405.13900">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> </div> </div> <p class="title is-5 mathjax"> Rehearsal-free Federated Domain-incremental Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+R">Rui Sun</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+J">Jiahua Dong</a>, <a href="/search/cs?searchtype=author&query=Ojha%2C+V">Varun Ojha</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</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="2405.13900v1-abstract-short" style="display: inline;"> We introduce a rehearsal-free federated domain incremental learning framework, RefFiL, based on a global prompt-sharing paradigm to alleviate catastrophic forgetting challenges in federated domain-incremental learning, where unseen domains are continually learned. Typical methods for mitigating forgetting, such as the use of additional datasets and the retention of private data from earlier tasks,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.13900v1-abstract-full').style.display = 'inline'; document.getElementById('2405.13900v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.13900v1-abstract-full" style="display: none;"> We introduce a rehearsal-free federated domain incremental learning framework, RefFiL, based on a global prompt-sharing paradigm to alleviate catastrophic forgetting challenges in federated domain-incremental learning, where unseen domains are continually learned. Typical methods for mitigating forgetting, such as the use of additional datasets and the retention of private data from earlier tasks, are not viable in federated learning (FL) due to devices' limited resources. Our method, RefFiL, addresses this by learning domain-invariant knowledge and incorporating various domain-specific prompts from the domains represented by different FL participants. A key feature of RefFiL is the generation of local fine-grained prompts by our domain adaptive prompt generator, which effectively learns from local domain knowledge while maintaining distinctive boundaries on a global scale. We also introduce a domain-specific prompt contrastive learning loss that differentiates between locally generated prompts and those from other domains, enhancing RefFiL's precision and effectiveness. Compared to existing methods, RefFiL significantly alleviates catastrophic forgetting without requiring extra memory space, making it ideal for privacy-sensitive and resource-constrained devices. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.13900v1-abstract-full').style.display = 'none'; document.getElementById('2405.13900v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.11252">arXiv:2405.11252</a> <span> [<a href="https://arxiv.org/pdf/2405.11252">pdf</a>, <a href="https://arxiv.org/format/2405.11252">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> </div> </div> <p class="title is-5 mathjax"> Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Miao%2C+X">Xingyu Miao</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Ojha%2C+V">Varun Ojha</a>, <a href="/search/cs?searchtype=author&query=Song%2C+J">Jun Song</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Long%2C+Y">Yang Long</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</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="2405.11252v1-abstract-short" style="display: inline;"> In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion Implicit Models (DDIM) inversion process. Unlike ISM which adopts the inversion process of DDIM to calculate on a single path, our TSM method leverages the inversi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.11252v1-abstract-full').style.display = 'inline'; document.getElementById('2405.11252v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.11252v1-abstract-full" style="display: none;"> In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval Score Matching (ISM) when using the Denoising Diffusion Implicit Models (DDIM) inversion process. Unlike ISM which adopts the inversion process of DDIM to calculate on a single path, our TSM method leverages the inversion process of DDIM to generate two paths from the same starting point for calculation. Since both paths start from the same starting point, TSM can reduce the accumulated error compared to ISM, thus alleviating the problem of pseudo ground truth inconsistency. TSM enhances the stability and consistency of the model's generated paths during the distillation process. We demonstrate this experimentally and further show that ISM is a special case of TSM. Furthermore, to optimize the current multi-stage optimization process from high-resolution text to 3D generation, we adopt Stable Diffusion XL for guidance. In response to the issues of abnormal replication and splitting caused by unstable gradients during the 3D Gaussian splatting process when using Stable Diffusion XL, we propose a pixel-by-pixel gradient clipping method. Extensive experiments show that our model significantly surpasses the state-of-the-art models in terms of visual quality and performance. Code: \url{https://github.com/xingy038/Dreamer-XL}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.11252v1-abstract-full').style.display = 'none'; document.getElementById('2405.11252v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.10674">arXiv:2405.10674</a> <span> [<a href="https://arxiv.org/pdf/2405.10674">pdf</a>, <a href="https://arxiv.org/format/2405.10674">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> From Sora What We Can See: A Survey of Text-to-Video Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+R">Rui Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yumin Zhang</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+J">Jiahao Sun</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shuoying Zhang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenqi Li</a>, <a href="/search/cs?searchtype=author&query=Duan%2C+H">Haoran Duan</a>, <a href="/search/cs?searchtype=author&query=Wei%2C+B">Bo Wei</a>, <a href="/search/cs?searchtype=author&query=Ranjan%2C+R">Rajiv Ranjan</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="2405.10674v1-abstract-short" style="display: inline;"> With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence. Sora, developed by OpenAI, which is capable of minute-level world-simulative abilities can be considered as a milestone on this developmental path. However, despite its notable successes, Sora still encounters various obstacles that need to be resolved. In this survey, we embark fr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.10674v1-abstract-full').style.display = 'inline'; document.getElementById('2405.10674v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.10674v1-abstract-full" style="display: none;"> With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence. Sora, developed by OpenAI, which is capable of minute-level world-simulative abilities can be considered as a milestone on this developmental path. However, despite its notable successes, Sora still encounters various obstacles that need to be resolved. In this survey, we embark from the perspective of disassembling Sora in text-to-video generation, and conducting a comprehensive review of literature, trying to answer the question, \textit{From Sora What We Can See}. Specifically, after basic preliminaries regarding the general algorithms are introduced, the literature is categorized from three mutually perpendicular dimensions: evolutionary generators, excellent pursuit, and realistic panorama. Subsequently, the widely used datasets and metrics are organized in detail. Last but more importantly, we identify several challenges and open problems in this domain and propose potential future directions for research and development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.10674v1-abstract-full').style.display = 'none'; document.getElementById('2405.10674v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 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">A comprehensive list of text-to-video generation studies in this survey is available at https://github.com/soraw-ai/Awesome-Text-to-Video-Generation</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.12464">arXiv:2312.12464</a> <span> [<a href="https://arxiv.org/pdf/2312.12464">pdf</a>, <a href="https://arxiv.org/format/2312.12464">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jaitly%2C+S">Sukriti Jaitly</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tanay Shah</a>, <a href="/search/cs?searchtype=author&query=Shugani%2C+A">Ashish Shugani</a>, <a href="/search/cs?searchtype=author&query=Grewal%2C+R+S">Razik Singh Grewal</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="2312.12464v2-abstract-short" style="display: inline;"> We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization techniques, including the standout LaTeX serialization method. This method significantly boosts the performance of LLMs in processing domain-specific datasets,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.12464v2-abstract-full').style.display = 'inline'; document.getElementById('2312.12464v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.12464v2-abstract-full" style="display: none;"> We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization techniques, including the standout LaTeX serialization method. This method significantly boosts the performance of LLMs in processing domain-specific datasets, Our method stands out for its memory efficiency and ability to fully utilize complex data structures. Through extensive experimentation, including various serialization approaches like feature combination and importance, we demonstrate our work's superiority in accuracy and efficiency over traditional models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.12464v2-abstract-full').style.display = 'none'; document.getElementById('2312.12464v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">4 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.09460">arXiv:2312.09460</a> <span> [<a href="https://arxiv.org/pdf/2312.09460">pdf</a>, <a href="https://arxiv.org/format/2312.09460">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Taming Waves: A Physically-Interpretable Machine Learning Framework for Realizable Control of Wave Dynamics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tristan Shah</a>, <a href="/search/cs?searchtype=author&query=Amirkulova%2C+F">Feruza Amirkulova</a>, <a href="/search/cs?searchtype=author&query=Tiomkin%2C+S">Stas Tiomkin</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="2312.09460v1-abstract-short" style="display: inline;"> Controlling systems governed by partial differential equations is an inherently hard problem. Specifically, control of wave dynamics is challenging due to additional physical constraints and intrinsic properties of wave phenomena such as dissipation, attenuation, reflection, and scattering. In this work, we introduce an environment designed for the study of the control of acoustic waves by actuate… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09460v1-abstract-full').style.display = 'inline'; document.getElementById('2312.09460v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.09460v1-abstract-full" style="display: none;"> Controlling systems governed by partial differential equations is an inherently hard problem. Specifically, control of wave dynamics is challenging due to additional physical constraints and intrinsic properties of wave phenomena such as dissipation, attenuation, reflection, and scattering. In this work, we introduce an environment designed for the study of the control of acoustic waves by actuated metamaterial designs. We utilize this environment for the development of a novel machine-learning method, based on deep neural networks, for efficiently learning the dynamics of an acoustic PDE from samples. Our model is fully interpretable and maps physical constraints and intrinsic properties of the real acoustic environment into its latent representation of information. Within our model we use a trainable perfectly matched layer to explicitly learn the property of acoustic energy dissipation. Our model can be used to predict and control scattered wave energy. The capabilities of our model are demonstrated on an important problem in acoustics, which is the minimization of total scattered energy. Furthermore, we show that the prediction of scattered energy by our model generalizes in time and can be extended to long time horizons. We make our code repository publicly available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09460v1-abstract-full').style.display = 'none'; document.getElementById('2312.09460v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.05623">arXiv:2312.05623</a> <span> [<a href="https://arxiv.org/pdf/2312.05623">pdf</a>, <a href="https://arxiv.org/format/2312.05623">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Impact of Urban Street Geometry on the Detection Probability of Automotive Radars </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+M+T">Mohammad Taha Shah</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+A">Ankit Kumar</a>, <a href="/search/cs?searchtype=author&query=Ghatak%2C+G">Gourab Ghatak</a>, <a href="/search/cs?searchtype=author&query=Ram%2C+S+S">Shobha Sundar Ram</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="2312.05623v1-abstract-short" style="display: inline;"> Prior works have analyzed the performance of millimeter wave automotive radars in the presence of diverse clutter and interference scenarios using stochastic geometry tools instead of more time-consuming measurement studies or system-level simulations. In these works, the distributions of radars or discrete clutter scatterers were modeled as Poisson point processes in the Euclidean space. However,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05623v1-abstract-full').style.display = 'inline'; document.getElementById('2312.05623v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.05623v1-abstract-full" style="display: none;"> Prior works have analyzed the performance of millimeter wave automotive radars in the presence of diverse clutter and interference scenarios using stochastic geometry tools instead of more time-consuming measurement studies or system-level simulations. In these works, the distributions of radars or discrete clutter scatterers were modeled as Poisson point processes in the Euclidean space. However, since most automotive radars are likely to be mounted on vehicles and road infrastructure, road geometries are an important factor that must be considered. Instead of considering each road geometry as an individual case for study, in this work, we model each case as a specific instance of an underlying Poisson line process and further model the distribution of vehicles on the road as a Poisson point process - forming a Poisson line Cox process. Then, through the use of stochastic geometry tools, we estimate the average number of interfering radars for specific road and vehicular densities and the effect of radar parameters such as noise and beamwidth on the radar detection metrics. The numerical results are validated with Monte Carlo simulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05623v1-abstract-full').style.display = 'none'; document.getElementById('2312.05623v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">Submitted to IEEE Radar Conference 2024 (RadarConf24)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.17994">arXiv:2310.17994</a> <span> [<a href="https://arxiv.org/pdf/2310.17994">pdf</a>, <a href="https://arxiv.org/format/2310.17994">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="Graphics">cs.GR</span> </div> </div> <p class="title is-5 mathjax"> ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sargent%2C+K">Kyle Sargent</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zizhang Li</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tanmay Shah</a>, <a href="/search/cs?searchtype=author&query=Herrmann%2C+C">Charles Herrmann</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+H">Hong-Xing Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yunzhi Zhang</a>, <a href="/search/cs?searchtype=author&query=Chan%2C+E+R">Eric Ryan Chan</a>, <a href="/search/cs?searchtype=author&query=Lagun%2C+D">Dmitry Lagun</a>, <a href="/search/cs?searchtype=author&query=Fei-Fei%2C+L">Li Fei-Fei</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+D">Deqing Sun</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jiajun Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.17994v2-abstract-short" style="display: inline;"> We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture obje… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17994v2-abstract-full').style.display = 'inline'; document.getElementById('2310.17994v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.17994v2-abstract-full" style="display: none;"> We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture object-centric, indoor, and outdoor scenes. To address issues from data mixture such as depth-scale ambiguity, we propose a novel camera conditioning parameterization and normalization scheme. Further, we observe that Score Distillation Sampling (SDS) tends to truncate the distribution of complex backgrounds during distillation of 360-degree scenes, and propose "SDS anchoring" to improve the diversity of synthesized novel views. Our model sets a new state-of-the-art result in LPIPS on the DTU dataset in the zero-shot setting, even outperforming methods specifically trained on DTU. We further adapt the challenging Mip-NeRF 360 dataset as a new benchmark for single-image novel view synthesis, and demonstrate strong performance in this setting. Our code and data are at http://kylesargent.github.io/zeronvs/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.17994v2-abstract-full').style.display = 'none'; document.getElementById('2310.17994v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to CVPR 2024. 12 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/2309.16859">arXiv:2309.16859</a> <span> [<a href="https://arxiv.org/pdf/2309.16859">pdf</a>, <a href="https://arxiv.org/format/2309.16859">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=B%C3%BChler%2C+M+C">Marcel C. B眉hler</a>, <a href="/search/cs?searchtype=author&query=Sarkar%2C+K">Kripasindhu Sarkar</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tanmay Shah</a>, <a href="/search/cs?searchtype=author&query=Li%2C+G">Gengyan Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+D">Daoye Wang</a>, <a href="/search/cs?searchtype=author&query=Helminger%2C+L">Leonhard Helminger</a>, <a href="/search/cs?searchtype=author&query=Orts-Escolano%2C+S">Sergio Orts-Escolano</a>, <a href="/search/cs?searchtype=author&query=Lagun%2C+D">Dmitry Lagun</a>, <a href="/search/cs?searchtype=author&query=Hilliges%2C+O">Otmar Hilliges</a>, <a href="/search/cs?searchtype=author&query=Beeler%2C+T">Thabo Beeler</a>, <a href="/search/cs?searchtype=author&query=Meka%2C+A">Abhimitra Meka</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.16859v1-abstract-short" style="display: inline;"> NeRFs have enabled highly realistic synthesis of human faces including complex appearance and reflectance effects of hair and skin. These methods typically require a large number of multi-view input images, making the process hardware intensive and cumbersome, limiting applicability to unconstrained settings. We propose a novel volumetric human face prior that enables the synthesis of ultra high-r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.16859v1-abstract-full').style.display = 'inline'; document.getElementById('2309.16859v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.16859v1-abstract-full" style="display: none;"> NeRFs have enabled highly realistic synthesis of human faces including complex appearance and reflectance effects of hair and skin. These methods typically require a large number of multi-view input images, making the process hardware intensive and cumbersome, limiting applicability to unconstrained settings. We propose a novel volumetric human face prior that enables the synthesis of ultra high-resolution novel views of subjects that are not part of the prior's training distribution. This prior model consists of an identity-conditioned NeRF, trained on a dataset of low-resolution multi-view images of diverse humans with known camera calibration. A simple sparse landmark-based 3D alignment of the training dataset allows our model to learn a smooth latent space of geometry and appearance despite a limited number of training identities. A high-quality volumetric representation of a novel subject can be obtained by model fitting to 2 or 3 camera views of arbitrary resolution. Importantly, our method requires as few as two views of casually captured images as input at inference time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.16859v1-abstract-full').style.display = 'none'; document.getElementById('2309.16859v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.11877">arXiv:2308.11877</a> <span> [<a href="https://arxiv.org/pdf/2308.11877">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Integrated Image and Location Analysis for Wound Classification: A Deep Learning Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Patel%2C+Y">Yash Patel</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tirth Shah</a>, <a href="/search/cs?searchtype=author&query=Dhar%2C+M+K">Mrinal Kanti Dhar</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+T">Taiyu Zhang</a>, <a href="/search/cs?searchtype=author&query=Niezgoda%2C+J">Jeffrey Niezgoda</a>, <a href="/search/cs?searchtype=author&query=Gopalakrishnan%2C+S">Sandeep Gopalakrishnan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+Z">Zeyun Yu</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="2308.11877v2-abstract-short" style="display: inline;"> The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative multi-modal network based on a deep convolutional neural network for categorizing wounds into four categories: diabetic, pressure, surgical, and venous ulcers. Our multi-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11877v2-abstract-full').style.display = 'inline'; document.getElementById('2308.11877v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.11877v2-abstract-full" style="display: none;"> The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative multi-modal network based on a deep convolutional neural network for categorizing wounds into four categories: diabetic, pressure, surgical, and venous ulcers. Our multi-modal network uses wound images and their corresponding body locations for more precise classification. A unique aspect of our methodology is incorporating a body map system that facilitates accurate wound location tagging, improving upon traditional wound image classification techniques. A distinctive feature of our approach is the integration of models such as VGG16, ResNet152, and EfficientNet within a novel architecture. This architecture includes elements like spatial and channel-wise Squeeze-and-Excitation modules, Axial Attention, and an Adaptive Gated Multi-Layer Perceptron, providing a robust foundation for classification. Our multi-modal network was trained and evaluated on two distinct datasets comprising relevant images and corresponding location information. Notably, our proposed network outperformed traditional methods, reaching an accuracy range of 74.79% to 100% for Region of Interest (ROI) without location classifications, 73.98% to 100% for ROI with location classifications, and 78.10% to 100% for whole image classifications. This marks a significant enhancement over previously reported performance metrics in the literature. Our results indicate the potential of our multi-modal network as an effective decision-support tool for wound image classification, paving the way for its application in various clinical contexts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11877v2-abstract-full').style.display = 'none'; document.getElementById('2308.11877v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 August, 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/2307.06392">arXiv:2307.06392</a> <span> [<a href="https://arxiv.org/pdf/2307.06392">pdf</a>, <a href="https://arxiv.org/format/2307.06392">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</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="Tissues and Organs">q-bio.TO</span> </div> </div> <p class="title is-5 mathjax"> Deep learning-based Segmentation of Rabbit fetal skull with limited and sub-optimal annotations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Soans%2C+R">Rajath Soans</a>, <a href="/search/cs?searchtype=author&query=Gleason%2C+A">Alexa Gleason</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tosha Shah</a>, <a href="/search/cs?searchtype=author&query=Miller%2C+C">Corey Miller</a>, <a href="/search/cs?searchtype=author&query=Robinson%2C+B">Barbara Robinson</a>, <a href="/search/cs?searchtype=author&query=Brannen%2C+K">Kimberly Brannen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+A">Antong Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.06392v1-abstract-short" style="display: inline;"> In this paper, we propose a deep learning-based method to segment the skeletal structures in the micro-CT images of Dutch-Belted rabbit fetuses which can assist in the assessment of drug-induced skeletal abnormalities as a required study in developmental and reproductive toxicology (DART). Our strategy leverages sub-optimal segmentation labels of 22 skull bones from 26 micro-CT volumes and maps th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.06392v1-abstract-full').style.display = 'inline'; document.getElementById('2307.06392v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.06392v1-abstract-full" style="display: none;"> In this paper, we propose a deep learning-based method to segment the skeletal structures in the micro-CT images of Dutch-Belted rabbit fetuses which can assist in the assessment of drug-induced skeletal abnormalities as a required study in developmental and reproductive toxicology (DART). Our strategy leverages sub-optimal segmentation labels of 22 skull bones from 26 micro-CT volumes and maps them to 250 unlabeled volumes on which a deep CNN-based segmentation model is trained. In the experiments, our model was able to achieve an average Dice Similarity Coefficient (DSC) of 0.89 across all bones on the testing set, and 14 out of the 26 skull bones reached average DSC >0.93. Our next steps are segmenting the whole body followed by developing a model to classify abnormalities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.06392v1-abstract-full').style.display = 'none'; document.getElementById('2307.06392v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted short paper - MIDL 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.13743">arXiv:2303.13743</a> <span> [<a href="https://arxiv.org/pdf/2303.13743">pdf</a>, <a href="https://arxiv.org/format/2303.13743">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> </div> </div> <p class="title is-5 mathjax"> TEGLO: High Fidelity Canonical Texture Mapping from Single-View Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Vinod%2C+V">Vishal Vinod</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tanmay Shah</a>, <a href="/search/cs?searchtype=author&query=Lagun%2C+D">Dmitry Lagun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.13743v1-abstract-short" style="display: inline;"> Recent work in Neural Fields (NFs) learn 3D representations from class-specific single view image collections. However, they are unable to reconstruct the input data preserving high-frequency details. Further, these methods do not disentangle appearance from geometry and hence are not suitable for tasks such as texture transfer and editing. In this work, we propose TEGLO (Textured EG3D-GLO) for le… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.13743v1-abstract-full').style.display = 'inline'; document.getElementById('2303.13743v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.13743v1-abstract-full" style="display: none;"> Recent work in Neural Fields (NFs) learn 3D representations from class-specific single view image collections. However, they are unable to reconstruct the input data preserving high-frequency details. Further, these methods do not disentangle appearance from geometry and hence are not suitable for tasks such as texture transfer and editing. In this work, we propose TEGLO (Textured EG3D-GLO) for learning 3D representations from single view in-the-wild image collections for a given class of objects. We accomplish this by training a conditional Neural Radiance Field (NeRF) without any explicit 3D supervision. We equip our method with editing capabilities by creating a dense correspondence mapping to a 2D canonical space. We demonstrate that such mapping enables texture transfer and texture editing without requiring meshes with shared topology. Our key insight is that by mapping the input image pixels onto the texture space we can achieve near perfect reconstruction (>= 74 dB PSNR at 1024^2 resolution). Our formulation allows for high quality 3D consistent novel view synthesis with high-frequency details at megapixel image resolution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.13743v1-abstract-full').style.display = 'none'; document.getElementById('2303.13743v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.12848">arXiv:2303.12848</a> <span> [<a href="https://arxiv.org/pdf/2303.12848">pdf</a>, <a href="https://arxiv.org/format/2303.12848">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> </div> </div> <p class="title is-5 mathjax"> Test-time Detection and Repair of Adversarial Samples via Masked Autoencoder </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tsai%2C+Y">Yun-Yun Tsai</a>, <a href="/search/cs?searchtype=author&query=Chao%2C+J">Ju-Chin Chao</a>, <a href="/search/cs?searchtype=author&query=Wen%2C+A">Albert Wen</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zhaoyuan Yang</a>, <a href="/search/cs?searchtype=author&query=Mao%2C+C">Chengzhi Mao</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tapan Shah</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+J">Junfeng 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="2303.12848v3-abstract-short" style="display: inline;"> Training-time defenses, known as adversarial training, incur high training costs and do not generalize to unseen attacks. Test-time defenses solve these issues but most existing test-time defenses require adapting the model weights, therefore they do not work on frozen models and complicate model memory management. The only test-time defense that does not adapt model weights aims to adapt the inpu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.12848v3-abstract-full').style.display = 'inline'; document.getElementById('2303.12848v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.12848v3-abstract-full" style="display: none;"> Training-time defenses, known as adversarial training, incur high training costs and do not generalize to unseen attacks. Test-time defenses solve these issues but most existing test-time defenses require adapting the model weights, therefore they do not work on frozen models and complicate model memory management. The only test-time defense that does not adapt model weights aims to adapt the input with self-supervision tasks. However, we empirically found these self-supervision tasks are not sensitive enough to detect adversarial attacks accurately. In this paper, we propose DRAM, a novel defense method to detect and repair adversarial samples at test time via Masked autoencoder (MAE). We demonstrate how to use MAE losses to build a Kolmogorov-Smirnov test to detect adversarial samples. Moreover, we use the MAE losses to calculate input reversal vectors that repair adversarial samples resulting from previously unseen attacks. Results on large-scale ImageNet dataset show that, compared to all detection baselines evaluated, DRAM achieves the best detection rate (82% on average) on all eight adversarial attacks evaluated. For attack repair, DRAM improves the robust accuracy by 6% ~ 41% for standard ResNet50 and 3% ~ 8% for robust ResNet50 compared with the baselines that use contrastive learning and rotation prediction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.12848v3-abstract-full').style.display = 'none'; document.getElementById('2303.12848v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.05151">arXiv:2302.05151</a> <span> [<a href="https://arxiv.org/pdf/2302.05151">pdf</a>, <a href="https://arxiv.org/ps/2302.05151">ps</a>, <a href="https://arxiv.org/format/2302.05151">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> </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/10.1134/S1063773722110056">10.1134/S1063773722110056 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Binomial Line Cox Processes: Statistical Characterization and Applications in Wireless Network Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+M+T">Mohammad Taha Shah</a>, <a href="/search/cs?searchtype=author&query=Ghatak%2C+G">Gourab Ghatak</a>, <a href="/search/cs?searchtype=author&query=Sanyal%2C+S">Souradip Sanyal</a>, <a href="/search/cs?searchtype=author&query=Haenggi%2C+M">Martin Haenggi</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="2302.05151v1-abstract-short" style="display: inline;"> The current analysis of wireless networks whose transceivers are confined to streets is largely based on Poissonian models, such as Poisson line processes and Poisson line Cox processes. We demonstrate important scenarios where a model with a finite and deterministic number of streets, termed binomial line process, is more accurate. We characterize the statistical properties of the BLP and the cor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.05151v1-abstract-full').style.display = 'inline'; document.getElementById('2302.05151v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.05151v1-abstract-full" style="display: none;"> The current analysis of wireless networks whose transceivers are confined to streets is largely based on Poissonian models, such as Poisson line processes and Poisson line Cox processes. We demonstrate important scenarios where a model with a finite and deterministic number of streets, termed binomial line process, is more accurate. We characterize the statistical properties of the BLP and the corresponding binomial line Cox process and apply them to analyze the performance of a network whose access points are deployed along the streets of a city. Such a deployment scenario will be typical for 5G and future wireless networks. In order to obtain a fine-grained insight into the network performance, we derive the meta distribution of the signal-to-interference and noise ratio. Accordingly, we investigate the mean local delay in transmission and the density of successful transmission. These metrics, respectively, characterize the latency and coverage performance of the network and are key performance indicators of next-generation wireless systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.05151v1-abstract-full').style.display = 'none'; document.getElementById('2302.05151v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">Submitted to IEEE Transactions on Wireless Communications</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.13593">arXiv:2205.13593</a> <span> [<a href="https://arxiv.org/pdf/2205.13593">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </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/10.1155/2022/8338508">10.1155/2022/8338508 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Block Ciphers Substitution Box Generation Based on Natural Randomness in Underwater Acoustics and Knights Tour Chain </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khan%2C+M+F">Muhammad Fahad Khan</a>, <a href="/search/cs?searchtype=author&query=Saleem%2C+K">Khalid Saleem</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tariq Shah</a>, <a href="/search/cs?searchtype=author&query=Hazzazi%2C+M+M">Mohammad Mazyad Hazzazi</a>, <a href="/search/cs?searchtype=author&query=Bahkali%2C+I">Ismail Bahkali</a>, <a href="/search/cs?searchtype=author&query=Shukla%2C+P+K">Piyush Kumar Shukla</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="2205.13593v1-abstract-short" style="display: inline;"> The protection of confidential information is a global issue and block encryption algorithms are the most reliable option. The famous information theorist, Claude Shannon has given two desirable characteristics that should exist in a strong cipher which are substitution and permutation in their fundamental research on Communication Theory of Secrecy Systems. block ciphers strictly follow the subst… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.13593v1-abstract-full').style.display = 'inline'; document.getElementById('2205.13593v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.13593v1-abstract-full" style="display: none;"> The protection of confidential information is a global issue and block encryption algorithms are the most reliable option. The famous information theorist, Claude Shannon has given two desirable characteristics that should exist in a strong cipher which are substitution and permutation in their fundamental research on Communication Theory of Secrecy Systems. block ciphers strictly follow the substitution and permutation principle to generate a ciphertext. The actual strength of the block ciphers against several attacks is entirely based on its substitution characteristic, which is gained by using the S-Box. In the current literature, algebraic structure-based and chaos-based techniques are highly used for the construction of S-boxes because both these techniques have favourable features for S-box construction, but also various attacks of these techniques have been identified. True randomness has been universally recognized as the ideal method for cipher primitives design because true random numbers are unpredictable, irreversible, and unreproducible. The basic concept of the proposed technique is the extraction of true random bits from underwater acoustic waves and to design a novel technique for the dynamic generation of S-boxes using the chain of knights tour. The proposed method satisfies all standard evaluation tests of S-boxes construction and true random numbers generation. Two million bits have been analyzed using the NIST randomness test suite, and the results show that underwater sound waves are an impeccable entropy source for true randomness. Additionally, our dynamically generated S-boxes have better or equal strength, over the latest published S-boxes (2020 to 2021). According to our knowledge first time, this type of research has been done, in which natural randomness of underwater acoustic waves has been used for the construction of block cipher's S-Box <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.13593v1-abstract-full').style.display = 'none'; document.getElementById('2205.13593v1-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 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">17 pages, 5 figures, Journal</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 94-11 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> E.3 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Computational Intelligence and Neuroscience,2022 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.10453">arXiv:2201.10453</a> <span> [<a href="https://arxiv.org/pdf/2201.10453">pdf</a>, <a href="https://arxiv.org/format/2201.10453">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> The First AI4TSP Competition: Learning to Solve Stochastic Routing Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bliek%2C+L">Laurens Bliek</a>, <a href="/search/cs?searchtype=author&query=da+Costa%2C+P">Paulo da Costa</a>, <a href="/search/cs?searchtype=author&query=Afshar%2C+R+R">Reza Refaei Afshar</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yingqian Zhang</a>, <a href="/search/cs?searchtype=author&query=Catshoek%2C+T">Tom Catshoek</a>, <a href="/search/cs?searchtype=author&query=Vos%2C+D">Dani毛l Vos</a>, <a href="/search/cs?searchtype=author&query=Verwer%2C+S">Sicco Verwer</a>, <a href="/search/cs?searchtype=author&query=Schmitt-Ulms%2C+F">Fynn Schmitt-Ulms</a>, <a href="/search/cs?searchtype=author&query=Hottung%2C+A">Andr茅 Hottung</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tapan Shah</a>, <a href="/search/cs?searchtype=author&query=Sellmann%2C+M">Meinolf Sellmann</a>, <a href="/search/cs?searchtype=author&query=Tierney%2C+K">Kevin Tierney</a>, <a href="/search/cs?searchtype=author&query=Perreault-Lafleur%2C+C">Carl Perreault-Lafleur</a>, <a href="/search/cs?searchtype=author&query=Leboeuf%2C+C">Caroline Leboeuf</a>, <a href="/search/cs?searchtype=author&query=Bobbio%2C+F">Federico Bobbio</a>, <a href="/search/cs?searchtype=author&query=Pepin%2C+J">Justine Pepin</a>, <a href="/search/cs?searchtype=author&query=Silva%2C+W+A">Warley Almeida Silva</a>, <a href="/search/cs?searchtype=author&query=Gama%2C+R">Ricardo Gama</a>, <a href="/search/cs?searchtype=author&query=Fernandes%2C+H+L">Hugo L. Fernandes</a>, <a href="/search/cs?searchtype=author&query=Zaefferer%2C+M">Martin Zaefferer</a>, <a href="/search/cs?searchtype=author&query=L%C3%B3pez-Ib%C3%A1%C3%B1ez%2C+M">Manuel L贸pez-Ib谩帽ez</a>, <a href="/search/cs?searchtype=author&query=Irurozki%2C+E">Ekhine Irurozki</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="2201.10453v1-abstract-short" style="display: inline;"> This paper reports on the first international competition on AI for the traveling salesman problem (TSP) at the International Joint Conference on Artificial Intelligence 2021 (IJCAI-21). The TSP is one of the classical combinatorial optimization problems, with many variants inspired by real-world applications. This first competition asked the participants to develop algorithms to solve a time-depe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.10453v1-abstract-full').style.display = 'inline'; document.getElementById('2201.10453v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.10453v1-abstract-full" style="display: none;"> This paper reports on the first international competition on AI for the traveling salesman problem (TSP) at the International Joint Conference on Artificial Intelligence 2021 (IJCAI-21). The TSP is one of the classical combinatorial optimization problems, with many variants inspired by real-world applications. This first competition asked the participants to develop algorithms to solve a time-dependent orienteering problem with stochastic weights and time windows (TD-OPSWTW). It focused on two types of learning approaches: surrogate-based optimization and deep reinforcement learning. In this paper, we describe the problem, the setup of the competition, the winning methods, and give an overview of the results. The winning methods described in this work have advanced the state-of-the-art in using AI for stochastic routing problems. Overall, by organizing this competition we have introduced routing problems as an interesting problem setting for AI researchers. The simulator of the problem has been made open-source and can be used by other researchers as a benchmark for new AI methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.10453v1-abstract-full').style.display = 'none'; document.getElementById('2201.10453v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 January, 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">21 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T05 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.12548">arXiv:2111.12548</a> <span> [<a href="https://arxiv.org/pdf/2111.12548">pdf</a>, <a href="https://arxiv.org/format/2111.12548">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> AutoDC: Automated data-centric processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Z+Y">Zac Yung-Chun Liu</a>, <a href="/search/cs?searchtype=author&query=Roychowdhury%2C+S">Shoumik Roychowdhury</a>, <a href="/search/cs?searchtype=author&query=Tarlow%2C+S">Scott Tarlow</a>, <a href="/search/cs?searchtype=author&query=Nair%2C+A">Akash Nair</a>, <a href="/search/cs?searchtype=author&query=Badhe%2C+S">Shweta Badhe</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejas Shah</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.12548v1-abstract-short" style="display: inline;"> AutoML (automated machine learning) has been extensively developed in the past few years for the model-centric approach. As for the data-centric approach, the processes to improve the dataset, such as fixing incorrect labels, adding examples that represent edge cases, and applying data augmentation, are still very artisanal and expensive. Here we develop an automated data-centric tool (AutoDC), si… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.12548v1-abstract-full').style.display = 'inline'; document.getElementById('2111.12548v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.12548v1-abstract-full" style="display: none;"> AutoML (automated machine learning) has been extensively developed in the past few years for the model-centric approach. As for the data-centric approach, the processes to improve the dataset, such as fixing incorrect labels, adding examples that represent edge cases, and applying data augmentation, are still very artisanal and expensive. Here we develop an automated data-centric tool (AutoDC), similar to the purpose of AutoML, aims to speed up the dataset improvement processes. In our preliminary tests on 3 open source image classification datasets, AutoDC is estimated to reduce roughly 80% of the manual time for data improvement tasks, at the same time, improve the model accuracy by 10-15% with the fixed ML code. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.12548v1-abstract-full').style.display = 'none'; document.getElementById('2111.12548v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS 2021- Data-Centric AI (DCAI) workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2107.14382">arXiv:2107.14382</a> <span> [<a href="https://arxiv.org/pdf/2107.14382">pdf</a>, <a href="https://arxiv.org/format/2107.14382">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> </div> </div> <p class="title is-5 mathjax"> Exploring Low-light Object Detection Techniques </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Winston Chen</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejas Shah</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2107.14382v1-abstract-short" style="display: inline;"> Images acquired by computer vision systems under low light conditions have multiple characteristics like high noise, lousy illumination, reflectance, and bad contrast, which make object detection tasks difficult. Much work has been done to enhance images using various pixel manipulation techniques, as well as deep neural networks - some focused on improving the illumination, while some on reducing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.14382v1-abstract-full').style.display = 'inline'; document.getElementById('2107.14382v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.14382v1-abstract-full" style="display: none;"> Images acquired by computer vision systems under low light conditions have multiple characteristics like high noise, lousy illumination, reflectance, and bad contrast, which make object detection tasks difficult. Much work has been done to enhance images using various pixel manipulation techniques, as well as deep neural networks - some focused on improving the illumination, while some on reducing the noise. Similarly, considerable research has been done in object detection neural network models. In our work, we break down the problem into two phases: 1)First, we explore which image enhancement algorithm is more suited for object detection tasks, where accurate feature retrieval is more important than good image quality. Specifically, we look at basic histogram equalization techniques and unpaired image translation techniques. 2)In the second phase, we explore different object detection models that can be applied to the enhanced image. We conclude by comparing all results, calculating mean average precisions (mAP), and giving some directions for future work. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.14382v1-abstract-full').style.display = 'none'; document.getElementById('2107.14382v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 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/2107.13649">arXiv:2107.13649</a> <span> [<a href="https://arxiv.org/pdf/2107.13649">pdf</a>, <a href="https://arxiv.org/format/2107.13649">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</span> </div> </div> <p class="title is-5 mathjax"> Reuse Cache for Heterogeneous CPU-GPU Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejas Shah</a>, <a href="/search/cs?searchtype=author&query=Yogatama%2C+B">Bobbi Yogatama</a>, <a href="/search/cs?searchtype=author&query=Roarty%2C+K">Kyle Roarty</a>, <a href="/search/cs?searchtype=author&query=Dahman%2C+R">Rami Dahman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2107.13649v1-abstract-short" style="display: inline;"> It is generally observed that the fraction of live lines in shared last-level caches (SLLC) is very small for chip multiprocessors (CMPs). This can be tackled using promotion-based replacement policies like re-reference interval prediction (RRIP) instead of LRU, dead-block predictors, or reuse-based cache allocation schemes. In GPU systems, similar LLC issues are alleviated using various cache byp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.13649v1-abstract-full').style.display = 'inline'; document.getElementById('2107.13649v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2107.13649v1-abstract-full" style="display: none;"> It is generally observed that the fraction of live lines in shared last-level caches (SLLC) is very small for chip multiprocessors (CMPs). This can be tackled using promotion-based replacement policies like re-reference interval prediction (RRIP) instead of LRU, dead-block predictors, or reuse-based cache allocation schemes. In GPU systems, similar LLC issues are alleviated using various cache bypassing techniques. These issues are worsened in heterogeneous CPU-GPU systems because the two processors have different data access patterns and frequencies. GPUs generally work on streaming data, but have many more threads accessing memory as compared to CPUs. As such, most traditional cache replacement and allocation policies prove ineffective due to the higher number of cache accesses in GPU applications, resulting in higher allocation for GPU cache lines, despite their minimal reuse. In this work, we implement the Reuse Cache approach for heterogeneous CPU-GPU systems. The reuse cache is a decoupled tag/data SLLC which is designed to only store the data that is being accessed more than once. This design is based on the observation that most of the cache lines in the LLC are stored but do not get reused before being replaced. We find that the reuse cache achieves within 0.5% of the IPC gains of a statically partitioned LLC, while decreasing the area cost of the LLC by an average of 40%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2107.13649v1-abstract-full').style.display = 'none'; document.getElementById('2107.13649v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 5 figures, 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2105.14256">arXiv:2105.14256</a> <span> [<a href="https://arxiv.org/pdf/2105.14256">pdf</a>, <a href="https://arxiv.org/format/2105.14256">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TVT.2021.3136365">10.1109/TVT.2021.3136365 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Performance of Dual-Hop Relaying for OWC System Over Foggy Channel with Pointing Errors and Atmospheric Turbulence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+Z">Ziyaur Rahman</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T+N">Tejas Nimish Shah</a>, <a href="/search/cs?searchtype=author&query=Zafaruddin%2C+S+M">S. M. Zafaruddin</a>, <a href="/search/cs?searchtype=author&query=Chaubey%2C+V+K">V. K. Chaubey</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="2105.14256v2-abstract-short" style="display: inline;"> Optical wireless communication (OWC) over atmospheric turbulence and pointing errors is a well-studied topic. Still, there is limited research on signal fading due to random fog in an outdoor environment for terrestrial wireless communications. In this paper, we analyze the performance of a decode-and-forward (DF) relaying under the combined effect of random fog, pointing errors, and atmospheric t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.14256v2-abstract-full').style.display = 'inline'; document.getElementById('2105.14256v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2105.14256v2-abstract-full" style="display: none;"> Optical wireless communication (OWC) over atmospheric turbulence and pointing errors is a well-studied topic. Still, there is limited research on signal fading due to random fog in an outdoor environment for terrestrial wireless communications. In this paper, we analyze the performance of a decode-and-forward (DF) relaying under the combined effect of random fog, pointing errors, and atmospheric turbulence with a negligible line-of-sight (LOS) direct link. We consider a generalized model for the end-to-end channel with independent and not identically distributed (i.ni.d.) pointing errors, random fog with Gamma distributed attenuation coefficient, double generalized gamma (DGG) atmospheric turbulence, and asymmetrical distance between the source and destination. We develop density and distribution functions of signal-to-noise ratio (SNR) under the combined effect of random fog, pointing errors, and atmospheric turbulence (FPT) channel and distribution function for the combined channel with random fog and pointing errors (FP). Using the derived statistical results, we present analytical expressions of the outage probability, average SNR, ergodic rate, and average bit error rate (BER) for both FP and FPT channels in terms of OWC system parameters. We also develop simplified and asymptotic performance analysis to provide insight on the system behavior analytically under various practically relevant scenarios. We demonstrate the mutual effects of channel impairments and pointing errors on the OWC performance, and show that the relaying system provides significant performance improvement compared with the direct transmissions, especially when pointing errors and fog becomes more pronounced. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2105.14256v2-abstract-full').style.display = 'none'; document.getElementById('2105.14256v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 May, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 5 figures, 3 Tables. Accepted for publication in the IEEE Transactions on Vehicular Technology</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Vehicular Technology, Early Access, Dec 2021 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.10321">arXiv:2103.10321</a> <span> [<a href="https://arxiv.org/pdf/2103.10321">pdf</a>, <a href="https://arxiv.org/format/2103.10321">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Learning How to Optimize Black-Box Functions With Extreme Limits on the Number of Function Evaluations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ansotegui%2C+C">Carlos Ansotegui</a>, <a href="/search/cs?searchtype=author&query=Sellmann%2C+M">Meinolf Sellmann</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tapan Shah</a>, <a href="/search/cs?searchtype=author&query=Tierney%2C+K">Kevin Tierney</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.10321v1-abstract-short" style="display: inline;"> We consider black-box optimization in which only an extremely limited number of function evaluations, on the order of around 100, are affordable and the function evaluations must be performed in even fewer batches of a limited number of parallel trials. This is a typical scenario when optimizing variable settings that are very costly to evaluate, for example in the context of simulation-based opti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.10321v1-abstract-full').style.display = 'inline'; document.getElementById('2103.10321v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.10321v1-abstract-full" style="display: none;"> We consider black-box optimization in which only an extremely limited number of function evaluations, on the order of around 100, are affordable and the function evaluations must be performed in even fewer batches of a limited number of parallel trials. This is a typical scenario when optimizing variable settings that are very costly to evaluate, for example in the context of simulation-based optimization or machine learning hyperparameterization. We propose an original method that uses established approaches to propose a set of points for each batch and then down-selects from these candidate points to the number of trials that can be run in parallel. The key novelty of our approach lies in the introduction of a hyperparameterized method for down-selecting the number of candidates to the allowed batch-size, which is optimized offline using automated algorithm configuration. We tune this method for black box optimization and then evaluate on classical black box optimization benchmarks. Our results show that it is possible to learn how to combine evaluation points suggested by highly diverse black box optimization methods conditioned on the progress of the optimization. Compared with the state of the art in black box minimization and various other methods specifically geared towards few-shot minimization, we achieve an average reduction of 50\% of normalized cost, which is a highly significant improvement in performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.10321v1-abstract-full').style.display = 'none'; document.getElementById('2103.10321v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.09608">arXiv:2012.09608</a> <span> [<a href="https://arxiv.org/pdf/2012.09608">pdf</a>, <a href="https://arxiv.org/format/2012.09608">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Cost-sensitive Hierarchical Clustering for Dynamic Classifier Selection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sellmann%2C+M">Meinolf Sellmann</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tapan Shah</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="2012.09608v2-abstract-short" style="display: inline;"> We consider the dynamic classifier selection (DCS) problem: Given an ensemble of classifiers, we are to choose which classifier to use depending on the particular input vector that we get to classify. The problem is a special case of the general algorithm selection problem where we have multiple different algorithms we can employ to process a given input. We investigate if a method developed for g… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.09608v2-abstract-full').style.display = 'inline'; document.getElementById('2012.09608v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.09608v2-abstract-full" style="display: none;"> We consider the dynamic classifier selection (DCS) problem: Given an ensemble of classifiers, we are to choose which classifier to use depending on the particular input vector that we get to classify. The problem is a special case of the general algorithm selection problem where we have multiple different algorithms we can employ to process a given input. We investigate if a method developed for general algorithm selection named cost-sensitive hierarchical clustering (CSHC) is suited for DCS. We introduce some additions to the original CSHC method for the special case of choosing a classification algorithm and evaluate their impact on performance. We then compare with a number of state-of-the-art dynamic classifier selection methods. Our experimental results show that our modified CSHC algorithm compares favorably <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.09608v2-abstract-full').style.display = 'none'; document.getElementById('2012.09608v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.05285">arXiv:2011.05285</a> <span> [<a href="https://arxiv.org/pdf/2011.05285">pdf</a>, <a href="https://arxiv.org/format/2011.05285">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> </div> </div> <p class="title is-5 mathjax"> Explainable Knowledge Tracing Models for Big Data: Is Ensembling an Answer? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tirth Shah</a>, <a href="/search/cs?searchtype=author&query=Olson%2C+L">Lukas Olson</a>, <a href="/search/cs?searchtype=author&query=Sharma%2C+A">Aditya Sharma</a>, <a href="/search/cs?searchtype=author&query=Patel%2C+N">Nirmal Patel</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2011.05285v1-abstract-short" style="display: inline;"> In this paper, we describe our Knowledge Tracing model for the 2020 NeurIPS Education Challenge. We used a combination of 22 models to predict whether the students will answer a given question correctly or not. Our combination of different approaches allowed us to get an accuracy higher than any of the individual models, and the variation of our model types gave our solution better explainability,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.05285v1-abstract-full').style.display = 'inline'; document.getElementById('2011.05285v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.05285v1-abstract-full" style="display: none;"> In this paper, we describe our Knowledge Tracing model for the 2020 NeurIPS Education Challenge. We used a combination of 22 models to predict whether the students will answer a given question correctly or not. Our combination of different approaches allowed us to get an accuracy higher than any of the individual models, and the variation of our model types gave our solution better explainability, more alignment with learning science theories, and high predictive power. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.05285v1-abstract-full').style.display = 'none'; document.getElementById('2011.05285v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 1 figure</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.04837">arXiv:2010.04837</a> <span> [<a href="https://arxiv.org/pdf/2010.04837">pdf</a>, <a href="https://arxiv.org/format/2010.04837">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> CurbScan: Curb Detection and Tracking Using Multi-Sensor Fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baek%2C+I">Iljoo Baek</a>, <a href="/search/cs?searchtype=author&query=Tai%2C+T">Tzu-Chieh Tai</a>, <a href="/search/cs?searchtype=author&query=Bhat%2C+M">Manoj Bhat</a>, <a href="/search/cs?searchtype=author&query=Ellango%2C+K">Karun Ellango</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tarang Shah</a>, <a href="/search/cs?searchtype=author&query=Fuseini%2C+K">Kamal Fuseini</a>, <a href="/search/cs?searchtype=author&query=Ragunathan"> Ragunathan</a>, <a href="/search/cs?searchtype=author&query=Rajkumar"> Rajkumar</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="2010.04837v2-abstract-short" style="display: inline;"> Reliable curb detection is critical for safe autonomous driving in urban contexts. Curb detection and tracking are also useful in vehicle localization and path planning. Past work utilized a 3D LiDAR sensor to determine accurate distance information and the geometric attributes of curbs. However, such an approach requires dense point cloud data and is also vulnerable to false positives from obstac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.04837v2-abstract-full').style.display = 'inline'; document.getElementById('2010.04837v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.04837v2-abstract-full" style="display: none;"> Reliable curb detection is critical for safe autonomous driving in urban contexts. Curb detection and tracking are also useful in vehicle localization and path planning. Past work utilized a 3D LiDAR sensor to determine accurate distance information and the geometric attributes of curbs. However, such an approach requires dense point cloud data and is also vulnerable to false positives from obstacles present on both road and off-road areas. In this paper, we propose an approach to detect and track curbs by fusing together data from multiple sensors: sparse LiDAR data, a mono camera and low-cost ultrasonic sensors. The detection algorithm is based on a single 3D LiDAR and a mono camera sensor used to detect candidate curb features and it effectively removes false positives arising from surrounding static and moving obstacles. The detection accuracy of the tracking algorithm is boosted by using Kalman filter-based prediction and fusion with lateral distance information from low-cost ultrasonic sensors. We next propose a line-fitting algorithm that yields robust results for curb locations. Finally, we demonstrate the practical feasibility of our solution by testing in different road environments and evaluating our implementation in a real vehicle\footnote{Demo video clips demonstrating our algorithm have been uploaded to Youtube: https://www.youtube.com/watch?v=w5MwsdWhcy4, https://www.youtube.com/watch?v=Gd506RklfG8.}. Our algorithm maintains over 90\% accuracy within 4.5-22 meters and 0-14 meters for the KITTI dataset and our dataset respectively, and its average processing time per frame is approximately 10 ms on Intel i7 x86 and 100ms on NVIDIA Xavier board. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.04837v2-abstract-full').style.display = 'none'; document.getElementById('2010.04837v2-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 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to IEEE ITSC-2020 conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1910.06428">arXiv:1910.06428</a> <span> [<a href="https://arxiv.org/pdf/1910.06428">pdf</a>, <a href="https://arxiv.org/format/1910.06428">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Restoration of marker occluded hematoxylin and eosin stained whole slide histology images using generative adversarial networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Venkatesh%2C+B">Bairavi Venkatesh</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tosha Shah</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+A">Antong Chen</a>, <a href="/search/cs?searchtype=author&query=Ghafurian%2C+S">Soheil Ghafurian</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="1910.06428v1-abstract-short" style="display: inline;"> It is common for pathologists to annotate specific regions of the tissue, such as tumor, directly on the glass slide with markers. Although this practice was helpful prior to the advent of histology whole slide digitization, it often occludes important details which are increasingly relevant to immuno-oncology due to recent advancements in digital pathology imaging techniques. The current work use… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.06428v1-abstract-full').style.display = 'inline'; document.getElementById('1910.06428v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1910.06428v1-abstract-full" style="display: none;"> It is common for pathologists to annotate specific regions of the tissue, such as tumor, directly on the glass slide with markers. Although this practice was helpful prior to the advent of histology whole slide digitization, it often occludes important details which are increasingly relevant to immuno-oncology due to recent advancements in digital pathology imaging techniques. The current work uses a generative adversarial network with cycle loss to remove these annotations while still maintaining the underlying structure of the tissue by solving an image-to-image translation problem. We train our network on up to 300 whole slide images with marker inks and show that 70% of the corrected image patches are indistinguishable from originally uncontaminated image tissue to a human expert. This portion increases 97% when we replace the human expert with a deep residual network. We demonstrated the fidelity of the method to the original image by calculating the correlation between image gradient magnitudes. We observed a revival of up to 94,000 nuclei per slide in our dataset, the majority of which were located on tissue border. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.06428v1-abstract-full').style.display = 'none'; document.getElementById('1910.06428v1-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 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1910.00078">arXiv:1910.00078</a> <span> [<a href="https://arxiv.org/pdf/1910.00078">pdf</a>, <a href="https://arxiv.org/format/1910.00078">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> MIOpen: An Open Source Library For Deep Learning Primitives </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Khan%2C+J">Jehandad Khan</a>, <a href="/search/cs?searchtype=author&query=Fultz%2C+P">Paul Fultz</a>, <a href="/search/cs?searchtype=author&query=Tamazov%2C+A">Artem Tamazov</a>, <a href="/search/cs?searchtype=author&query=Lowell%2C+D">Daniel Lowell</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Chao Liu</a>, <a href="/search/cs?searchtype=author&query=Melesse%2C+M">Michael Melesse</a>, <a href="/search/cs?searchtype=author&query=Nandhimandalam%2C+M">Murali Nandhimandalam</a>, <a href="/search/cs?searchtype=author&query=Nasyrov%2C+K">Kamil Nasyrov</a>, <a href="/search/cs?searchtype=author&query=Perminov%2C+I">Ilya Perminov</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejash Shah</a>, <a href="/search/cs?searchtype=author&query=Filippov%2C+V">Vasilii Filippov</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+J">Jing Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jing Zhou</a>, <a href="/search/cs?searchtype=author&query=Natarajan%2C+B">Bragadeesh Natarajan</a>, <a href="/search/cs?searchtype=author&query=Daga%2C+M">Mayank Daga</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="1910.00078v1-abstract-short" style="display: inline;"> Deep Learning has established itself to be a common occurrence in the business lexicon. The unprecedented success of deep learning in recent years can be attributed to: abundance of data, availability of gargantuan compute capabilities offered by GPUs, and adoption of open-source philosophy by the researchers and industry. Deep neural networks can be decomposed into a series of different operators… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.00078v1-abstract-full').style.display = 'inline'; document.getElementById('1910.00078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1910.00078v1-abstract-full" style="display: none;"> Deep Learning has established itself to be a common occurrence in the business lexicon. The unprecedented success of deep learning in recent years can be attributed to: abundance of data, availability of gargantuan compute capabilities offered by GPUs, and adoption of open-source philosophy by the researchers and industry. Deep neural networks can be decomposed into a series of different operators. MIOpen, AMD's open-source deep learning primitives library for GPUs, provides highly optimized implementations of such operators, shielding researchers from internal implementation details and hence, accelerating the time to discovery. This paper introduces MIOpen and provides details about the internal workings of the library and supported features. MIOpen innovates on several fronts, such as implementing fusion to optimize for memory bandwidth and GPU launch overheads, providing an auto-tuning infrastructure to overcome the large design space of problem configurations, and implementing different algorithms to optimize convolutions for different filter and input sizes. MIOpen is one of the first libraries to publicly support the bfloat16 data-type for convolutions, allowing efficient training at lower precision without the loss of accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.00078v1-abstract-full').style.display = 'none'; document.getElementById('1910.00078v1-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 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1403.7766">arXiv:1403.7766</a> <span> [<a href="https://arxiv.org/pdf/1403.7766">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Automated Decision Support across Medical and Oral Health Domains with Semantic Web Technologies </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tejal Shah</a>, <a href="/search/cs?searchtype=author&query=Rabhi%2C+F">Fethi Rabhi</a>, <a href="/search/cs?searchtype=author&query=Ray%2C+P">Pradeep Ray</a>, <a href="/search/cs?searchtype=author&query=Taylor%2C+K">Kerry Taylor</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="1403.7766v1-abstract-short" style="display: inline;"> Research has shown that the general health and oral health of an individual are closely related. Accordingly, current practice of isolating the information base of medical and oral health domains can be dangerous and detrimental to the health of the individual. However, technical issues such as heterogeneous data collection and storage formats, limited sharing of patient information and lack of de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1403.7766v1-abstract-full').style.display = 'inline'; document.getElementById('1403.7766v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1403.7766v1-abstract-full" style="display: none;"> Research has shown that the general health and oral health of an individual are closely related. Accordingly, current practice of isolating the information base of medical and oral health domains can be dangerous and detrimental to the health of the individual. However, technical issues such as heterogeneous data collection and storage formats, limited sharing of patient information and lack of decision support over the shared information are the principal reasons for the current state of affairs. To address these issues, the following research investigates the development and application of a cross-domain ontology and rules to build an evidence-based and reusable knowledge base consisting of the inter-dependent conditions from the two domains. Through example implementation of the knowledge base in Protege, we demonstrate the effectiveness of our approach in reasoning over and providing decision support for cross-domain patient information. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1403.7766v1-abstract-full').style.display = 'none'; document.getElementById('1403.7766v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 March, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2014. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The paper has been published at the 24th Australasian Conference on Information Systems, 4-6 Dec 2013, Melbourne. The paper can be found at: http://mo.bf.rmit.edu.au/acis2013/382.pdf</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1310.1571">arXiv:1310.1571</a> <span> [<a href="https://arxiv.org/pdf/1310.1571">pdf</a>, <a href="https://arxiv.org/format/1310.1571">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> </div> </div> <p class="title is-5 mathjax"> Transmit Beamforming for MIMO Communication Systems with Low Precision ADC at the Receiver </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tapan Shah</a>, <a href="/search/cs?searchtype=author&query=Dabeer%2C+O">Onkar Dabeer</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="1310.1571v1-abstract-short" style="display: inline;"> Multiple antenna systems have been extensively used by standards designing multi-gigabit communication systems operating in bandwidth of several GHz. In this paper, we study the use of transmitter (Tx) beamforming techniques to improve the performance of a MIMO system with a low precision ADC. We motivate an approach to use eigenmode transmit beamforming (which imposes a diagonal structure in the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1310.1571v1-abstract-full').style.display = 'inline'; document.getElementById('1310.1571v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1310.1571v1-abstract-full" style="display: none;"> Multiple antenna systems have been extensively used by standards designing multi-gigabit communication systems operating in bandwidth of several GHz. In this paper, we study the use of transmitter (Tx) beamforming techniques to improve the performance of a MIMO system with a low precision ADC. We motivate an approach to use eigenmode transmit beamforming (which imposes a diagonal structure in the complete MIMO system) and use an eigenmode power allocation which minimizes the uncoded BER of the finite precision system. Although we cannot guarantee optimality of this approach, we observe that even low with precision ADC, it performs comparably to full precision system with no eigenmode power allocation. For example, in a high throughput MIMO system with a finite precision ADC at the receiver, simulation results show that for a 3/4 LDPC coded 2x2 MIMO OFDM 16-QAM system with 3-bit precision ADC at the receiver, a BER of 0.0001 is achieved at an SNR of 26 dB. This is 1 dB better than that required for the same system with full precision but equal eigenmode power allocation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1310.1571v1-abstract-full').style.display = 'none'; document.getElementById('1310.1571v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 October, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2013. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1309.4373">arXiv:1309.4373</a> <span> [<a href="https://arxiv.org/pdf/1309.4373">pdf</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> </div> </div> <p class="title is-5 mathjax"> Energy optimization and Performance Analysis of Cluster Based Routing Protocols Extended from LEACH for WSNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aslam%2C+M">M. Aslam</a>, <a href="/search/cs?searchtype=author&query=Rasheed%2C+M+B">M. B. Rasheed</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">T. Shah</a>, <a href="/search/cs?searchtype=author&query=Rahim%2C+A">A. Rahim</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+Z+A">Z. A. Khan</a>, <a href="/search/cs?searchtype=author&query=Qasim%2C+U">U. Qasim</a>, <a href="/search/cs?searchtype=author&query=Qasim%2C+M+W">M. W. Qasim</a>, <a href="/search/cs?searchtype=author&query=Hassan%2C+A">A. Hassan</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+A">A. Khan</a>, <a href="/search/cs?searchtype=author&query=Javaid%2C+N">N. Javaid</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="1309.4373v1-abstract-short" style="display: inline;"> An energy efficient routing protocol is the major attentiveness for researcher in field of Wireless Sensor Networks (WSNs). In this paper, we present some energy efficient hierarchal routing protocols, prosper from conventional Low Energy Adaptive Clustering Hierarchy (LEACH) routing protocol. Fundamental objective of our consideration is to analyze, how these ex- tended routing protocols work in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1309.4373v1-abstract-full').style.display = 'inline'; document.getElementById('1309.4373v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1309.4373v1-abstract-full" style="display: none;"> An energy efficient routing protocol is the major attentiveness for researcher in field of Wireless Sensor Networks (WSNs). In this paper, we present some energy efficient hierarchal routing protocols, prosper from conventional Low Energy Adaptive Clustering Hierarchy (LEACH) routing protocol. Fundamental objective of our consideration is to analyze, how these ex- tended routing protocols work in order to optimize lifetime of network nodes and how quality of routing protocols is improved for WSNs. Furthermore, this paper also emphasizes on some issues experienced by LEACH and also explains how these issues are tackled by other enhanced routing protocols from classi- cal LEACH. We analytically compare the features and performance issues of each hierarchal routing protocol. We also simulate selected clustering routing protocols for our study in order to elaborate the enhancement achieved by ameliorate routing protocols. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1309.4373v1-abstract-full').style.display = 'none'; document.getElementById('1309.4373v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2013. </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">Journal of Basic and Applied Scientific Research, 2013. arXiv admin note: text overlap with arXiv:1207.2609</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1306.5381">arXiv:1306.5381</a> <span> [<a href="https://arxiv.org/pdf/1306.5381">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> RFID Technology Based Attendance Management System </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nainan%2C+S">Sumita Nainan</a>, <a href="/search/cs?searchtype=author&query=Parekh%2C+R">Romin Parekh</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tanvi Shah</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="1306.5381v1-abstract-short" style="display: inline;"> RFID is a nascent technology, deeply rooted by its early developments in using radar1 as a harbinger of adversary planes during World War II. A plethora of industries have leveraged the benefits of RFID technology for enhancements in sectors like military, sports, security, airline, animal farms, healthcare and other areas. Industry specific key applications of this technology include vehicle trac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1306.5381v1-abstract-full').style.display = 'inline'; document.getElementById('1306.5381v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1306.5381v1-abstract-full" style="display: none;"> RFID is a nascent technology, deeply rooted by its early developments in using radar1 as a harbinger of adversary planes during World War II. A plethora of industries have leveraged the benefits of RFID technology for enhancements in sectors like military, sports, security, airline, animal farms, healthcare and other areas. Industry specific key applications of this technology include vehicle tracking, automated inventory management, animal monitoring, secure store checkouts, supply chain management, automatic payment, sport timing technologies, etc. This paper introduces the distinctive components of RFID technology and focuses on its core competencies: scalability and security. It will be then supplemented by a detailed synopsis of an investigation conducted to test the feasibility and practicality of RFID technology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1306.5381v1-abstract-full').style.display = 'none'; document.getElementById('1306.5381v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 June, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2013. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 8 figures, 2 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68U04 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> B.1.1; B.2.3; B.4.1; B.4.2; C.5.3; D.3.2; D.4.4; E.1; H.4.1 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> International Journal of Computer Science Issues bearing paper ID 'IJCSI-2013-10-1-4801' was published in IJCSI Volume 10, Issue 1, January 2013 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1304.1459">arXiv:1304.1459</a> <span> [<a href="https://arxiv.org/pdf/1304.1459">pdf</a>, <a href="https://arxiv.org/ps/1304.1459">ps</a>, <a href="https://arxiv.org/format/1304.1459">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> </div> </div> <p class="title is-5 mathjax"> Bandwidth reduction in cognitive radio </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">Tariq Shah</a>, <a href="/search/cs?searchtype=author&query=Hussain%2C+S+A">Sayed Azmat Hussain</a>, <a href="/search/cs?searchtype=author&query=de+Andrade%2C+A+A">Antonio Aparecido de Andrade</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="1304.1459v1-abstract-short" style="display: inline;"> Due to mushroom development of wireless devices cognitive radio is used to resolve the bandwidth utilization and sacristy problem. The crafty usage of bandwidth in cognitive radio based on error correcting codes is ensured to accomodate un authorized user. This study proposes a transmission model by which a finite sequence of binary cyclic codes constructed by a binary BCH code of length… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1304.1459v1-abstract-full').style.display = 'inline'; document.getElementById('1304.1459v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1304.1459v1-abstract-full" style="display: none;"> Due to mushroom development of wireless devices cognitive radio is used to resolve the bandwidth utilization and sacristy problem. The crafty usage of bandwidth in cognitive radio based on error correcting codes is ensured to accomodate un authorized user. This study proposes a transmission model by which a finite sequence of binary cyclic codes constructed by a binary BCH code of length $n=2^{s}-1$, in which all codes have same error correction capability and code rate but sequentially increasing code lengths greater than $n$. Initially all these codes are carrying data of their corresponding primary users. A transmission pattern is planned in the sprit of interweave model deals the transmission parameters; modulation scheme, bandwidth and code rate. Whenever, any of the primary users having mod of transmission, the binary cyclic code, is not using its allocated bandwidth, the user having its data built by binary BCH code enter and exploit the free path as a secondary user. Eventually whenever the primary user with $W$ bandwidth having binary BCH code for its data transmission, change its status as a secondary user, it just requires the bandwidth less than $W$. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1304.1459v1-abstract-full').style.display = 'none'; document.getElementById('1304.1459v1-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 April, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2013. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 11T71; 68P30; 94A15 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1212.4106">arXiv:1212.4106</a> <span> [<a href="https://arxiv.org/pdf/1212.4106">pdf</a>, <a href="https://arxiv.org/ps/1212.4106">ps</a>, <a href="https://arxiv.org/format/1212.4106">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> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/INMIC.2012.6511504">10.1109/INMIC.2012.6511504 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Energy Efficient Sleep Awake Aware (EESAA) Intelligent Sensor Network Routing Protocol </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+T">T. Shah</a>, <a href="/search/cs?searchtype=author&query=Javaid%2C+N">N. Javaid</a>, <a href="/search/cs?searchtype=author&query=Qureshi%2C+T+N">T. N. Qureshi</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="1212.4106v1-abstract-short" style="display: inline;"> Wireless Sensor Networks (WSNs), with growing applications in the environment which are not within human reach have been addressed tremendously in the recent past. For optimized working of network many routing algorithms have been proposed, mainly focusing energy efficiency, network lifetime, clustering processes. Considering homogeneity of network, we proposed Energy Efficient Sleep Awake Aware (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1212.4106v1-abstract-full').style.display = 'inline'; document.getElementById('1212.4106v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1212.4106v1-abstract-full" style="display: none;"> Wireless Sensor Networks (WSNs), with growing applications in the environment which are not within human reach have been addressed tremendously in the recent past. For optimized working of network many routing algorithms have been proposed, mainly focusing energy efficiency, network lifetime, clustering processes. Considering homogeneity of network, we proposed Energy Efficient Sleep Awake Aware (EESAA) intelligent routing protocol for WSNs. In our proposed technique we evaluate and enhance certain issues like network stability, network lifetime and cluster head selection process. Utilizing the concept of characteristical pairing among sensor nodes energy utilization is optimized. Simulation results show that our proposed protocolnificantly improved the <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1212.4106v1-abstract-full').style.display = 'none'; document.getElementById('1212.4106v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 December, 2012; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2012. </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">15th IEEE International Multi Topic Conference (INMIC12), 2012</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1207.3595">arXiv:1207.3595</a> <span> [<a href="https://arxiv.org/pdf/1207.3595">pdf</a>, <a href="https://arxiv.org/ps/1207.3595">ps</a>, <a href="https://arxiv.org/format/1207.3595">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> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/SECON.2012.6275763">10.1109/SECON.2012.6275763 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> CEEC: Centralized Energy Efficient Clustering A New Routing Protocol for WSNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aslam%2C+M">M. Aslam</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+T">T. Shah</a>, <a href="/search/cs?searchtype=author&query=Javaid%2C+N">N. Javaid</a>, <a href="/search/cs?searchtype=author&query=Rahim%2C+A">A. Rahim</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+Z">Z. Rahman</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+Z+A">Z. A. Khan</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="1207.3595v1-abstract-short" style="display: inline;"> Energy efficient routing protocol for Wireless Sensor Networks (WSNs) is one of the most challenging task for researcher. Hierarchical routing protocols have been proved more energy efficient routing protocols, as compare to flat and location based routing protocols. Heterogeneity of nodes with respect to their energy level, has also added extra lifespan for sensor network. In this paper, we propo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1207.3595v1-abstract-full').style.display = 'inline'; document.getElementById('1207.3595v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1207.3595v1-abstract-full" style="display: none;"> Energy efficient routing protocol for Wireless Sensor Networks (WSNs) is one of the most challenging task for researcher. Hierarchical routing protocols have been proved more energy efficient routing protocols, as compare to flat and location based routing protocols. Heterogeneity of nodes with respect to their energy level, has also added extra lifespan for sensor network. In this paper, we propose a Centralized Energy Efficient Clustering (CEEC) routing protocol. We design the CEEC for three level heterogeneous network. CEEC can also be implemented in multi-level heterogeneity of networks. For initial practical, we design and analyze CEEC for three level advance heterogeneous network. In CEEC, whole network area is divided into three equal regions, in which nodes with same energy are spread in same region. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1207.3595v1-abstract-full').style.display = 'none'; document.getElementById('1207.3595v1-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, 2012; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2012. </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">9th IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks (SECON), Seoul, Korea June, 2012</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Shah%2C+T&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Shah%2C+T&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Shah%2C+T&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository