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 148 results for author: <span class="mathjax">Pereira, F</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=Pereira%2C+F">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="Pereira, F"> </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=Pereira%2C+F&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="Pereira, F"> <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=Pereira%2C+F&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Pereira%2C+F&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Pereira%2C+F&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Pereira%2C+F&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </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/2410.09236">arXiv:2410.09236</a> <span> [<a href="https://arxiv.org/pdf/2410.09236">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Infant Crying Detection with Gradient Boosting for Improved Emotional and Mental Health Diagnostics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lee%2C+K">Kyunghun Lee</a>, <a href="/search/cs?searchtype=author&query=Henry%2C+L+M">Lauren M. Henry</a>, <a href="/search/cs?searchtype=author&query=Hansen%2C+E">Eleanor Hansen</a>, <a href="/search/cs?searchtype=author&query=Tandilashvili%2C+E">Elizabeth Tandilashvili</a>, <a href="/search/cs?searchtype=author&query=Wakschlag%2C+L+S">Lauren S. Wakschlag</a>, <a href="/search/cs?searchtype=author&query=Norton%2C+E">Elizabeth Norton</a>, <a href="/search/cs?searchtype=author&query=Pine%2C+D+S">Daniel S. Pine</a>, <a href="/search/cs?searchtype=author&query=Brotman%2C+M+A">Melissa A. Brotman</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</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="2410.09236v1-abstract-short" style="display: inline;"> Infant crying can serve as a crucial indicator of various physiological and emotional states. This paper introduces a comprehensive approach for detecting infant cries within audio data. We integrate Meta's Wav2Vec with traditional audio features, such as Mel-frequency cepstral coefficients (MFCCs), chroma, and spectral contrast, employing Gradient Boosting Machines (GBM) for cry classification. W… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09236v1-abstract-full').style.display = 'inline'; document.getElementById('2410.09236v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.09236v1-abstract-full" style="display: none;"> Infant crying can serve as a crucial indicator of various physiological and emotional states. This paper introduces a comprehensive approach for detecting infant cries within audio data. We integrate Meta's Wav2Vec with traditional audio features, such as Mel-frequency cepstral coefficients (MFCCs), chroma, and spectral contrast, employing Gradient Boosting Machines (GBM) for cry classification. We validate our approach on a real-world dataset, demonstrating significant performance improvements over existing methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.09236v1-abstract-full').style.display = 'none'; document.getElementById('2410.09236v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.08003">arXiv:2410.08003</a> <span> [<a href="https://arxiv.org/pdf/2410.08003">pdf</a>, <a href="https://arxiv.org/format/2410.08003">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"> More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shaier%2C+S">Sagi Shaier</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</a>, <a href="/search/cs?searchtype=author&query=von+der+Wense%2C+K">Katharina von der Wense</a>, <a href="/search/cs?searchtype=author&query=Hunter%2C+L+E">Lawrence E Hunter</a>, <a href="/search/cs?searchtype=author&query=Jones%2C+M">Matt Jones</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="2410.08003v2-abstract-short" style="display: inline;"> The evolution of biological neural systems has led to both modularity and sparse coding, which enables efficiency in energy usage, and robustness across the diversity of tasks in the lifespan. In contrast, standard neural networks rely on dense, non-specialized architectures, where all model parameters are simultaneously updated to learn multiple tasks, leading to representation interference. Curr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08003v2-abstract-full').style.display = 'inline'; document.getElementById('2410.08003v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.08003v2-abstract-full" style="display: none;"> The evolution of biological neural systems has led to both modularity and sparse coding, which enables efficiency in energy usage, and robustness across the diversity of tasks in the lifespan. In contrast, standard neural networks rely on dense, non-specialized architectures, where all model parameters are simultaneously updated to learn multiple tasks, leading to representation interference. Current sparse neural network approaches aim to alleviate this issue, but are often hindered by limitations such as 1) trainable gating functions that cause representation collapse; 2) non-overlapping experts that result in redundant computation and slow learning; and 3) reliance on explicit input or task IDs that impose significant constraints on flexibility and scalability. In this paper we propose Conditionally Overlapping Mixture of ExperTs (COMET), a general deep learning method that addresses these challenges by inducing a modular, sparse architecture with an exponential number of overlapping experts. COMET replaces the trainable gating function used in Sparse Mixture of Experts with a fixed, biologically inspired random projection applied to individual input representations. This design causes the degree of expert overlap to depend on input similarity, so that similar inputs tend to share more parameters. This facilitates positive knowledge transfer, resulting in faster learning and improved generalization. We demonstrate the effectiveness of COMET on a range of tasks, including image classification, language modeling, and regression, using several popular deep learning architectures. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.08003v2-abstract-full').style.display = 'none'; document.getElementById('2410.08003v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.18574">arXiv:2409.18574</a> <span> [<a href="https://arxiv.org/pdf/2409.18574">pdf</a>, <a href="https://arxiv.org/format/2409.18574">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"> Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Costa%2C+M">Miguel Costa</a>, <a href="/search/cs?searchtype=author&query=Petersen%2C+M+W">Morten W. Petersen</a>, <a href="/search/cs?searchtype=author&query=Vandervoort%2C+A">Arthur Vandervoort</a>, <a href="/search/cs?searchtype=author&query=Drews%2C+M">Martin Drews</a>, <a href="/search/cs?searchtype=author&query=Morrissey%2C+K">Karyn Morrissey</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C. Pereira</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="2409.18574v1-abstract-short" style="display: inline;"> Due to climate change the frequency and intensity of extreme rainfall events, which contribute to urban flooding, are expected to increase in many places. These floods can damage transport infrastructure and disrupt mobility, highlighting the need for cities to adapt to escalating risks. Reinforcement learning (RL) serves as a powerful tool for uncovering optimal adaptation strategies, determining… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18574v1-abstract-full').style.display = 'inline'; document.getElementById('2409.18574v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.18574v1-abstract-full" style="display: none;"> Due to climate change the frequency and intensity of extreme rainfall events, which contribute to urban flooding, are expected to increase in many places. These floods can damage transport infrastructure and disrupt mobility, highlighting the need for cities to adapt to escalating risks. Reinforcement learning (RL) serves as a powerful tool for uncovering optimal adaptation strategies, determining how and where to deploy adaptation measures effectively, even under significant uncertainty. In this study, we leverage RL to identify the most effective timing and locations for implementing measures, aiming to reduce both direct and indirect impacts of flooding. Our framework integrates climate change projections of future rainfall events and floods, models city-wide motorized trips, and quantifies direct and indirect impacts on infrastructure and mobility. Preliminary results suggest that our RL-based approach can significantly enhance decision-making by prioritizing interventions in specific urban areas and identifying the optimal periods for their implementation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.18574v1-abstract-full').style.display = 'none'; document.getElementById('2409.18574v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 September, 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/2409.08130">arXiv:2409.08130</a> <span> [<a href="https://arxiv.org/pdf/2409.08130">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machine </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guarda%2C+A+F+R">Andr茅 F. R. Guarda</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+N+M+M">Nuno M. M. Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Fernando Pereira</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="2409.08130v1-abstract-short" style="display: inline;"> Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the difference. Deep learning has emerged as a powerful tool in this domain, offering advanced techniques for compressing point clouds more efficiently than conventiona… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08130v1-abstract-full').style.display = 'inline'; document.getElementById('2409.08130v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08130v1-abstract-full" style="display: none;"> Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the difference. Deep learning has emerged as a powerful tool in this domain, offering advanced techniques for compressing point clouds more efficiently than conventional coding methods while also allowing effective computer vision tasks performed in the compressed domain thus, for the first time, making available a common compressed visual representation effective for both man and machine. Taking advantage of this potential, JPEG has recently finalized the JPEG Pleno Learning-based Point Cloud Coding (PCC) standard offering efficient lossy coding of static point clouds, targeting both human visualization and machine processing by leveraging deep learning models for geometry and color coding. The geometry is processed directly in its original 3D form using sparse convolutional neural networks, while the color data is projected onto 2D images and encoded using the also learning-based JPEG AI standard. The goal of this paper is to provide a complete technical description of the JPEG PCC standard, along with a thorough benchmarking of its performance against the state-of-the-art, while highlighting its main strengths and weaknesses. In terms of compression performance, JPEG PCC outperforms the conventional MPEG PCC standards, especially in geometry coding, achieving significant rate reductions. Color compression performance is less competitive but this is overcome by the power of a full learning-based coding framework for both geometry and color and the associated effective compressed domain processing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08130v1-abstract-full').style.display = 'none'; document.getElementById('2409.08130v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 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">28 pages, 12 figures, submitted to IEEE Access</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.15531">arXiv:2407.15531</a> <span> [<a href="https://arxiv.org/pdf/2407.15531">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> </div> </div> <p class="title is-5 mathjax"> Double Deep Learning-based Event Data Coding and Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Seleem%2C+A">Abdelrahman Seleem</a>, <a href="/search/cs?searchtype=author&query=Guarda%2C+A+F+R">Andr茅 F. R. Guarda</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+N+M+M">Nuno M. M. Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Fernando Pereira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.15531v1-abstract-short" style="display: inline;"> Event cameras have the ability to capture asynchronous per-pixel brightness changes, called "events", offering advantages over traditional frame-based cameras for computer vision applications. Efficiently coding event data is critical for transmission and storage, given the significant volume of events. This paper proposes a novel double deep learning-based architecture for both event data coding… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15531v1-abstract-full').style.display = 'inline'; document.getElementById('2407.15531v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.15531v1-abstract-full" style="display: none;"> Event cameras have the ability to capture asynchronous per-pixel brightness changes, called "events", offering advantages over traditional frame-based cameras for computer vision applications. Efficiently coding event data is critical for transmission and storage, given the significant volume of events. This paper proposes a novel double deep learning-based architecture for both event data coding and classification, using a point cloud-based representation for events. In this context, the conversions from events to point clouds and back to events are key steps in the proposed solution, and therefore its impact is evaluated in terms of compression and classification performance. Experimental results show that it is possible to achieve a classification performance of compressed events which is similar to one of the original events, even after applying a lossy point cloud codec, notably the recent learning-based JPEG Pleno Point Cloud Coding standard, with a clear rate reduction. Experimental results also demonstrate that events coded using JPEG PCC achieve better classification performance than those coded using the conventional lossy MPEG Geometry-based Point Cloud Coding standard. Furthermore, the adoption of learning-based coding offers high potential for performing computer vision tasks in the compressed domain, which allows skipping the decoding stage while mitigating the impact of coding artifacts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.15531v1-abstract-full').style.display = 'none'; document.getElementById('2407.15531v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.14087">arXiv:2407.14087</a> <span> [<a href="https://arxiv.org/pdf/2407.14087">pdf</a>, <a href="https://arxiv.org/format/2407.14087">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"> Score Normalization for Demographic Fairness in Face Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Linghu%2C+Y">Yu Linghu</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+T+d+F">Tiago de Freitas Pereira</a>, <a href="/search/cs?searchtype=author&query=Ecabert%2C+C">Christophe Ecabert</a>, <a href="/search/cs?searchtype=author&query=Marcel%2C+S">S茅bastien Marcel</a>, <a href="/search/cs?searchtype=author&query=G%C3%BCnther%2C+M">Manuel G眉nther</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.14087v2-abstract-short" style="display: inline;"> Fair biometric algorithms have similar verification performance across different demographic groups given a single decision threshold. Unfortunately, for state-of-the-art face recognition networks, score distributions differ between demographics. Contrary to work that tries to align those distributions by extra training or fine-tuning, we solely focus on score post-processing methods. As proved, w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14087v2-abstract-full').style.display = 'inline'; document.getElementById('2407.14087v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.14087v2-abstract-full" style="display: none;"> Fair biometric algorithms have similar verification performance across different demographic groups given a single decision threshold. Unfortunately, for state-of-the-art face recognition networks, score distributions differ between demographics. Contrary to work that tries to align those distributions by extra training or fine-tuning, we solely focus on score post-processing methods. As proved, well-known sample-centered score normalization techniques, Z-norm and T-norm, do not improve fairness for high-security operating points. Thus, we extend the standard Z/T-norm to integrate demographic information in normalization. Additionally, we investigate several possibilities to incorporate cohort similarities for both genuine and impostor pairs per demographic to improve fairness across different operating points. We run experiments on two datasets with different demographics (gender and ethnicity) and show that our techniques generally improve the overall fairness of five state-of-the-art pre-trained face recognition networks, without downgrading verification performance. We also indicate that an equal contribution of False Match Rate (FMR) and False Non-Match Rate (FNMR) in fairness evaluation is required for the highest gains. Code and protocols are available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14087v2-abstract-full').style.display = 'none'; document.getElementById('2407.14087v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for presentation at IJCB 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/2406.20037">arXiv:2406.20037</a> <span> [<a href="https://arxiv.org/pdf/2406.20037">pdf</a>, <a href="https://arxiv.org/format/2406.20037">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="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> Explore as a Storm, Exploit as a Raindrop: On the Benefit of Fine-Tuning Kernel Schedulers with Coordinate Descent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Canesche%2C+M">Michael Canesche</a>, <a href="/search/cs?searchtype=author&query=Verma%2C+G">Gaurav Verma</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+M+Q">Fernando Magno Quintao Pereira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.20037v2-abstract-short" style="display: inline;"> Machine-learning models consist of kernels, which are algorithms applying operations on tensors -- data indexed by a linear combination of natural numbers. Examples of kernels include convolutions, transpositions, and vectorial products. There are many ways to implement a kernel. These implementations form the kernel's optimization space. Kernel scheduling is the problem of finding the best implem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.20037v2-abstract-full').style.display = 'inline'; document.getElementById('2406.20037v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.20037v2-abstract-full" style="display: none;"> Machine-learning models consist of kernels, which are algorithms applying operations on tensors -- data indexed by a linear combination of natural numbers. Examples of kernels include convolutions, transpositions, and vectorial products. There are many ways to implement a kernel. These implementations form the kernel's optimization space. Kernel scheduling is the problem of finding the best implementation, given an objective function -- typically execution speed. Kernel optimizers such as Ansor, Halide, and AutoTVM solve this problem via search heuristics, which combine two phases: exploration and exploitation. The first step evaluates many different kernel optimization spaces. The latter tries to improve the best implementations by investigating a kernel within the same space. For example, Ansor combines kernel generation through sketches for exploration and leverages an evolutionary algorithm to exploit the best sketches. In this work, we demonstrate the potential to reduce Ansor's search time while enhancing kernel quality by incorporating Droplet Search, an AutoTVM algorithm, into Ansor's exploration phase. The approach involves limiting the number of samples explored by Ansor, selecting the best, and exploiting it with a coordinate descent algorithm. By applying this approach to the first 300 kernels that Ansor generates, we usually obtain better kernels in less time than if we let Ansor analyze 10,000 kernels. This result has been replicated in 20 well-known deep-learning models (AlexNet, ResNet, VGG, DenseNet, etc.) running on four architectures: an AMD Ryzen 7 (x86), an NVIDIA A100 tensor core, an NVIDIA RTX 3080 GPU, and an ARM A64FX. A patch with this combined approach was approved in Ansor in February 2024. As evidence of the generality of this search methodology, a similar patch, achieving equally good results, was submitted to TVM's MetaSchedule in June 2024. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.20037v2-abstract-full').style.display = 'none'; document.getElementById('2406.20037v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">22 pages, 19 figures, original work</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68N20 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> D.3.4 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.10437">arXiv:2406.10437</a> <span> [<a href="https://arxiv.org/pdf/2406.10437">pdf</a>, <a href="https://arxiv.org/format/2406.10437">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Mathematical Software">cs.MS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Differential Geometry">math.DG</span> </div> </div> <p class="title is-5 mathjax"> Learning from landmarks, curves, surfaces, and shapes in Geomstats </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pereira%2C+L+F">Lu铆s F. Pereira</a>, <a href="/search/cs?searchtype=author&query=Brigant%2C+A+L">Alice Le Brigant</a>, <a href="/search/cs?searchtype=author&query=Myers%2C+A">Adele Myers</a>, <a href="/search/cs?searchtype=author&query=Hartman%2C+E">Emmanuel Hartman</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+A">Amil Khan</a>, <a href="/search/cs?searchtype=author&query=Tuerkoen%2C+M">Malik Tuerkoen</a>, <a href="/search/cs?searchtype=author&query=Dold%2C+T">Trey Dold</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+M">Mengyang Gu</a>, <a href="/search/cs?searchtype=author&query=Su%C3%A1rez-Serrato%2C+P">Pablo Su谩rez-Serrato</a>, <a href="/search/cs?searchtype=author&query=Miolane%2C+N">Nina Miolane</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.10437v1-abstract-short" style="display: inline;"> We introduce the shape module of the Python package Geomstats to analyze shapes of objects represented as landmarks, curves and surfaces across fields of natural sciences and engineering. The shape module first implements widely used shape spaces, such as the Kendall shape space, as well as elastic spaces of discrete curves and surfaces. The shape module further implements the abstract mathematica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10437v1-abstract-full').style.display = 'inline'; document.getElementById('2406.10437v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10437v1-abstract-full" style="display: none;"> We introduce the shape module of the Python package Geomstats to analyze shapes of objects represented as landmarks, curves and surfaces across fields of natural sciences and engineering. The shape module first implements widely used shape spaces, such as the Kendall shape space, as well as elastic spaces of discrete curves and surfaces. The shape module further implements the abstract mathematical structures of group actions, fiber bundles, quotient spaces and associated Riemannian metrics which allow users to build their own shape spaces. The Riemannian geometry tools enable users to compare, average, interpolate between shapes inside a given shape space. These essential operations can then be leveraged to perform statistics and machine learning on shape data. We present the object-oriented implementation of the shape module along with illustrative examples and show how it can be used to perform statistics and machine learning on shape spaces. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10437v1-abstract-full').style.display = 'none'; document.getElementById('2406.10437v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Report number:</span> MPIM-Bonn-2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.09066">arXiv:2406.09066</a> <span> [<a href="https://arxiv.org/pdf/2406.09066">pdf</a>, <a href="https://arxiv.org/format/2406.09066">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Impermanent Identifiers: Enhanced Source Code Comprehension and Refactoring </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guerra%2C+E+M">Eduardo Martins Guerra</a>, <a href="/search/cs?searchtype=author&query=Ivo%2C+A+A+S">Andre A. S. Ivo</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+O">Fernando O. Pereira</a>, <a href="/search/cs?searchtype=author&query=Robbes%2C+R">Romain Robbes</a>, <a href="/search/cs?searchtype=author&query=Janes%2C+A">Andrea Janes</a>, <a href="/search/cs?searchtype=author&query=Silveira%2C+F+F">Fabio Fagundes Silveira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.09066v2-abstract-short" style="display: inline;"> In response to the prevailing challenges in contemporary software development, this article introduces an innovative approach to code augmentation centered around Impermanent Identifiers. The primary goal is to enhance the software development experience by introducing dynamic identifiers that adapt to changing contexts, facilitating more efficient interactions between developers and source code,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09066v2-abstract-full').style.display = 'inline'; document.getElementById('2406.09066v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.09066v2-abstract-full" style="display: none;"> In response to the prevailing challenges in contemporary software development, this article introduces an innovative approach to code augmentation centered around Impermanent Identifiers. The primary goal is to enhance the software development experience by introducing dynamic identifiers that adapt to changing contexts, facilitating more efficient interactions between developers and source code, ultimately advancing comprehension, maintenance, and collaboration in software development. Additionally, this study rigorously evaluates the adoption and acceptance of Impermanent Identifiers within the software development landscape. Through a comprehensive empirical examination, we investigate how developers perceive and integrate this approach into their daily programming practices, exploring perceived benefits, potential barriers, and factors influencing its adoption. In summary, this article charts a new course for code augmentation, proposing Impermanent Identifiers as its cornerstone while assessing their feasibility and acceptance among developers. This interdisciplinary research seeks to contribute to the continuous improvement of software development practices and the progress of code augmentation technology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.09066v2-abstract-full').style.display = 'none'; document.getElementById('2406.09066v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">to be published in The Journal of Systems & Software</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.06550">arXiv:2406.06550</a> <span> [<a href="https://arxiv.org/pdf/2406.06550">pdf</a>, <a href="https://arxiv.org/format/2406.06550">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> </div> </div> <p class="title is-5 mathjax"> ChiBench: a Benchmark Suite for Testing Electronic Design Automation Tools </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sumitani%2C+R">Rafael Sumitani</a>, <a href="/search/cs?searchtype=author&query=Amorim%2C+J+V">Jo茫o Victor Amorim</a>, <a href="/search/cs?searchtype=author&query=Mafra%2C+A">Augusto Mafra</a>, <a href="/search/cs?searchtype=author&query=Crepalde%2C+M">Mirlaine Crepalde</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+M+Q">Fernando Magno Quint茫o Pereira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.06550v1-abstract-short" style="display: inline;"> Electronic Design Automation (EDA) tools are software applications used by engineers in the design, development, simulation, and verification of electronic systems and integrated circuits. These tools typically process specifications written in a Hardware Description Language (HDL), such as Verilog, SystemVerilog or VHDL. Thus, effective testing of these tools requires benchmark suites written in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.06550v1-abstract-full').style.display = 'inline'; document.getElementById('2406.06550v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.06550v1-abstract-full" style="display: none;"> Electronic Design Automation (EDA) tools are software applications used by engineers in the design, development, simulation, and verification of electronic systems and integrated circuits. These tools typically process specifications written in a Hardware Description Language (HDL), such as Verilog, SystemVerilog or VHDL. Thus, effective testing of these tools requires benchmark suites written in these languages. However, while there exist some open benchmark suites for these languages, they tend to consist of only a handful of specifications. This paper, in contrast, presents ChiBench, a comprehensive suite comprising 50 thousand Verilog programs. These programs were sourced from GitHub repositories and curated using Verible's syntactic analyzer and Jasper(TM)'s HDL semantic analyzer. Since its inception, ChiBench has already revealed bugs in public tools like Verible's obfuscator and parser. In addition to explaining some of these case studies, this paper demonstrates how ChiBench can be used to evaluate the asymptotic complexity and code coverage of typical electronic design automation tools. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.06550v1-abstract-full').style.display = 'none'; document.getElementById('2406.06550v1-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> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 6 figures, 12 references</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68N15 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> D.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.17080">arXiv:2404.17080</a> <span> [<a href="https://arxiv.org/pdf/2404.17080">pdf</a>, <a href="https://arxiv.org/format/2404.17080">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Discrete Mathematics">cs.DM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Combinatorics">math.CO</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/10.4230/LIPIcs.ESA.2024.94">10.4230/LIPIcs.ESA.2024.94 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Solving the Graph Burning Problem for Large Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pereira%2C+F+d+C">Felipe de Carvalho Pereira</a>, <a href="/search/cs?searchtype=author&query=de+Rezende%2C+P+J">Pedro Jussieu de Rezende</a>, <a href="/search/cs?searchtype=author&query=Yunes%2C+T">Tallys Yunes</a>, <a href="/search/cs?searchtype=author&query=Morato%2C+L+F+B">Luiz Fernando Batista Morato</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.17080v2-abstract-short" style="display: inline;"> We propose an exact algorithm for the Graph Burning Problem ($\texttt{GBP}$), an NP-hard optimization problem that models the spread of influence on social networks. Given a graph $G$ with vertex set $V$, the objective is to find a sequence of $k$ vertices in $V$, namely, $v_1, v_2, \dots, v_k$, such that $k$ is minimum and $\bigcup_{i = 1}^{k} \{u\! \in\! V\! : d(u, v_i) \leq k - i\} = V$, where… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.17080v2-abstract-full').style.display = 'inline'; document.getElementById('2404.17080v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.17080v2-abstract-full" style="display: none;"> We propose an exact algorithm for the Graph Burning Problem ($\texttt{GBP}$), an NP-hard optimization problem that models the spread of influence on social networks. Given a graph $G$ with vertex set $V$, the objective is to find a sequence of $k$ vertices in $V$, namely, $v_1, v_2, \dots, v_k$, such that $k$ is minimum and $\bigcup_{i = 1}^{k} \{u\! \in\! V\! : d(u, v_i) \leq k - i\} = V$, where $d(u,v)$ denotes the distance between $u$ and $v$. We formulate the problem as a set covering integer programming model and design a row generation algorithm for the $\texttt{GBP}$. Our method exploits the fact that a very small number of covering constraints is often sufficient for solving the integer model, allowing the corresponding rows to be generated on demand. To date, the most efficient exact algorithm for the $\texttt{GBP}$, denoted here by $\texttt{GDCA}$, is able to obtain optimal solutions for graphs with up to 14,000 vertices within two hours of execution. In comparison, our algorithm finds provably optimal solutions approximately 236 times faster, on average, than $\texttt{GDCA}$. For larger graphs, memory space becomes a limiting factor for $\texttt{GDCA}$. Our algorithm, however, solves real-world instances with almost 200,000 vertices in less than 35 seconds, increasing the size of graphs for which optimal solutions are known by a factor of 14. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.17080v2-abstract-full').style.display = 'none'; document.getElementById('2404.17080v2-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">v1</span> submitted 25 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 1 figure and 2 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68R05 (Primary) 05C85; 90C10 (Secondary) <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> G.2.1 </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> A Row Generation Algorithm for Finding Optimal Burning Sequences of Large Graphs. In 32nd Annual European Symposium on Algorithms (ESA 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 308, pp. 94:1-94:17, 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.07934">arXiv:2404.07934</a> <span> [<a href="https://arxiv.org/pdf/2404.07934">pdf</a>, <a href="https://arxiv.org/format/2404.07934">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Goal Recognition via Linear Programming </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Meneguzzi%2C+F">Felipe Meneguzzi</a>, <a href="/search/cs?searchtype=author&query=Santos%2C+L+R+d+A">Lu铆sa R. de A. Santos</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+R+F">Ramon Fraga Pereira</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+A+G">Andr茅 G. Pereira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.07934v1-abstract-short" style="display: inline;"> Goal Recognition is the task by which an observer aims to discern the goals that correspond to plans that comply with the perceived behavior of subject agents given as a sequence of observations. Research on Goal Recognition as Planning encompasses reasoning about the model of a planning task, the observations, and the goals using planning techniques, resulting in very efficient recognition approa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07934v1-abstract-full').style.display = 'inline'; document.getElementById('2404.07934v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07934v1-abstract-full" style="display: none;"> Goal Recognition is the task by which an observer aims to discern the goals that correspond to plans that comply with the perceived behavior of subject agents given as a sequence of observations. Research on Goal Recognition as Planning encompasses reasoning about the model of a planning task, the observations, and the goals using planning techniques, resulting in very efficient recognition approaches. In this article, we design novel recognition approaches that rely on the Operator-Counting framework, proposing new constraints, and analyze their constraints' properties both theoretically and empirically. The Operator-Counting framework is a technique that efficiently computes heuristic estimates of cost-to-goal using Integer/Linear Programming (IP/LP). In the realm of theory, we prove that the new constraints provide lower bounds on the cost of plans that comply with observations. We also provide an extensive empirical evaluation to assess how the new constraints improve the quality of the solution, and we found that they are especially informed in deciding which goals are unlikely to be part of the solution. Our novel recognition approaches have two pivotal advantages: first, they employ new IP/LP constraints for efficiently recognizing goals; second, we show how the new IP/LP constraints can improve the recognition of goals under both partial and noisy observability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07934v1-abstract-full').style.display = 'none'; document.getElementById('2404.07934v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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 JAIR April 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/2404.07698">arXiv:2404.07698</a> <span> [<a href="https://arxiv.org/pdf/2404.07698">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimator </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mari%2C+D">Daniele Mari</a>, <a href="/search/cs?searchtype=author&query=Guarda%2C+A+F+R">Andr茅 F. R. Guarda</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+N+M+M">Nuno M. M. Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Milani%2C+S">Simone Milani</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Fernando Pereira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.07698v2-abstract-short" style="display: inline;"> The widespread usage of point clouds (PC) for immersive visual applications has resulted in the use of very heterogeneous receiving conditions and devices, notably in terms of network, hardware, and display capabilities. In this scenario, quality scalability, i.e., the ability to reconstruct a signal at different qualities by progressively decoding a single bitstream, is a major requirement that h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07698v2-abstract-full').style.display = 'inline'; document.getElementById('2404.07698v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07698v2-abstract-full" style="display: none;"> The widespread usage of point clouds (PC) for immersive visual applications has resulted in the use of very heterogeneous receiving conditions and devices, notably in terms of network, hardware, and display capabilities. In this scenario, quality scalability, i.e., the ability to reconstruct a signal at different qualities by progressively decoding a single bitstream, is a major requirement that has yet to be conveniently addressed, notably in most learning-based PC coding solutions. This paper proposes a quality scalability scheme, named Scalable Quality Hyperprior (SQH), adaptable to learning-based static point cloud geometry codecs, which uses a Quality-conditioned Latents Probability Estimator (QuLPE) to decode a high-quality version of a PC learning-based representation, based on an available lower quality base layer. SQH is integrated in the future JPEG PC coding standard, allowing to create a layered bitstream that can be used to progressively decode the PC geometry with increasing quality and fidelity. Experimental results show that SQH offers the quality scalability feature with very limited or no compression performance penalty at all when compared with the corresponding non-scalable solution, thus preserving the significant compression gains over other state-of-the-art PC codecs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07698v2-abstract-full').style.display = 'none'; document.getElementById('2404.07698v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at ICIP 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/2403.18788">arXiv:2403.18788</a> <span> [<a href="https://arxiv.org/pdf/2403.18788">pdf</a>, <a href="https://arxiv.org/format/2403.18788">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> <p class="title is-5 mathjax"> Peregrine: ML-based Malicious Traffic Detection for Terabit Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Amado%2C+J+R">Jo茫o Romeiras Amado</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</a>, <a href="/search/cs?searchtype=author&query=Pissarra%2C+D">David Pissarra</a>, <a href="/search/cs?searchtype=author&query=Signorello%2C+S">Salvatore Signorello</a>, <a href="/search/cs?searchtype=author&query=Correia%2C+M">Miguel Correia</a>, <a href="/search/cs?searchtype=author&query=Ramos%2C+F+M+V">Fernando M. V. Ramos</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.18788v1-abstract-short" style="display: inline;"> Malicious traffic detectors leveraging machine learning (ML), namely those incorporating deep learning techniques, exhibit impressive detection capabilities across multiple attacks. However, their effectiveness becomes compromised when deployed in networks handling Terabit-speed traffic. In practice, these systems require substantial traffic sampling to reconcile the high data plane packet rates w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.18788v1-abstract-full').style.display = 'inline'; document.getElementById('2403.18788v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.18788v1-abstract-full" style="display: none;"> Malicious traffic detectors leveraging machine learning (ML), namely those incorporating deep learning techniques, exhibit impressive detection capabilities across multiple attacks. However, their effectiveness becomes compromised when deployed in networks handling Terabit-speed traffic. In practice, these systems require substantial traffic sampling to reconcile the high data plane packet rates with the comparatively slower processing speeds of ML detection. As sampling significantly reduces traffic observability, it fundamentally undermines their detection capability. We present Peregrine, an ML-based malicious traffic detector for Terabit networks. The key idea is to run the detection process partially in the network data plane. Specifically, we offload the detector's ML feature computation to a commodity switch. The Peregrine switch processes a diversity of features per-packet, at Tbps line rates - three orders of magnitude higher than the fastest detector - to feed the ML-based component in the control plane. Our offloading approach presents a distinct advantage. While, in practice, current systems sample raw traffic, in Peregrine sampling occurs after feature computation. This essential trait enables computing features over all traffic, significantly enhancing detection performance. The Peregrine detector is not only effective for Terabit networks, but it is also energy- and cost-efficient. Further, by shifting a compute-heavy component to the switch, it saves precious CPU cycles and improves detection throughput. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.18788v1-abstract-full').style.display = 'none'; document.getElementById('2403.18788v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.08295">arXiv:2403.08295</a> <span> [<a href="https://arxiv.org/pdf/2403.08295">pdf</a>, <a href="https://arxiv.org/format/2403.08295">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Gemma: Open Models Based on Gemini Research and Technology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gemma+Team"> Gemma Team</a>, <a href="/search/cs?searchtype=author&query=Mesnard%2C+T">Thomas Mesnard</a>, <a href="/search/cs?searchtype=author&query=Hardin%2C+C">Cassidy Hardin</a>, <a href="/search/cs?searchtype=author&query=Dadashi%2C+R">Robert Dadashi</a>, <a href="/search/cs?searchtype=author&query=Bhupatiraju%2C+S">Surya Bhupatiraju</a>, <a href="/search/cs?searchtype=author&query=Pathak%2C+S">Shreya Pathak</a>, <a href="/search/cs?searchtype=author&query=Sifre%2C+L">Laurent Sifre</a>, <a href="/search/cs?searchtype=author&query=Rivi%C3%A8re%2C+M">Morgane Rivi猫re</a>, <a href="/search/cs?searchtype=author&query=Kale%2C+M+S">Mihir Sanjay Kale</a>, <a href="/search/cs?searchtype=author&query=Love%2C+J">Juliette Love</a>, <a href="/search/cs?searchtype=author&query=Tafti%2C+P">Pouya Tafti</a>, <a href="/search/cs?searchtype=author&query=Hussenot%2C+L">L茅onard Hussenot</a>, <a href="/search/cs?searchtype=author&query=Sessa%2C+P+G">Pier Giuseppe Sessa</a>, <a href="/search/cs?searchtype=author&query=Chowdhery%2C+A">Aakanksha Chowdhery</a>, <a href="/search/cs?searchtype=author&query=Roberts%2C+A">Adam Roberts</a>, <a href="/search/cs?searchtype=author&query=Barua%2C+A">Aditya Barua</a>, <a href="/search/cs?searchtype=author&query=Botev%2C+A">Alex Botev</a>, <a href="/search/cs?searchtype=author&query=Castro-Ros%2C+A">Alex Castro-Ros</a>, <a href="/search/cs?searchtype=author&query=Slone%2C+A">Ambrose Slone</a>, <a href="/search/cs?searchtype=author&query=H%C3%A9liou%2C+A">Am茅lie H茅liou</a>, <a href="/search/cs?searchtype=author&query=Tacchetti%2C+A">Andrea Tacchetti</a>, <a href="/search/cs?searchtype=author&query=Bulanova%2C+A">Anna Bulanova</a>, <a href="/search/cs?searchtype=author&query=Paterson%2C+A">Antonia Paterson</a>, <a href="/search/cs?searchtype=author&query=Tsai%2C+B">Beth Tsai</a>, <a href="/search/cs?searchtype=author&query=Shahriari%2C+B">Bobak Shahriari</a> , et al. (83 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="2403.08295v4-abstract-short" style="display: inline;"> This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate strong performance across academic benchmarks for language understanding, reasoning, and safety. We release two sizes of models (2 billion and 7 billion parameters), and provide both pretrained and fine-tuned checkpoints. Ge… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08295v4-abstract-full').style.display = 'inline'; document.getElementById('2403.08295v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.08295v4-abstract-full" style="display: none;"> This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate strong performance across academic benchmarks for language understanding, reasoning, and safety. We release two sizes of models (2 billion and 7 billion parameters), and provide both pretrained and fine-tuned checkpoints. Gemma outperforms similarly sized open models on 11 out of 18 text-based tasks, and we present comprehensive evaluations of safety and responsibility aspects of the models, alongside a detailed description of model development. We believe the responsible release of LLMs is critical for improving the safety of frontier models, and for enabling the next wave of LLM innovations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08295v4-abstract-full').style.display = 'none'; document.getElementById('2403.08295v4-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.11973">arXiv:2402.11973</a> <span> [<a href="https://arxiv.org/pdf/2402.11973">pdf</a>, <a href="https://arxiv.org/format/2402.11973">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"> Bayesian Active Learning for Censored Regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=H%C3%BCttel%2C+F+B">Frederik Boe H眉ttel</a>, <a href="/search/cs?searchtype=author&query=Riis%2C+C">Christoffer Riis</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+F">Filipe Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C芒mara Pereira</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="2402.11973v1-abstract-short" style="display: inline;"> Bayesian active learning is based on information theoretical approaches that focus on maximising the information that new observations provide to the model parameters. This is commonly done by maximising the Bayesian Active Learning by Disagreement (BALD) acquisitions function. However, we highlight that it is challenging to estimate BALD when the new data points are subject to censorship, where o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.11973v1-abstract-full').style.display = 'inline'; document.getElementById('2402.11973v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.11973v1-abstract-full" style="display: none;"> Bayesian active learning is based on information theoretical approaches that focus on maximising the information that new observations provide to the model parameters. This is commonly done by maximising the Bayesian Active Learning by Disagreement (BALD) acquisitions function. However, we highlight that it is challenging to estimate BALD when the new data points are subject to censorship, where only clipped values of the targets are observed. To address this, we derive the entropy and the mutual information for censored distributions and derive the BALD objective for active learning in censored regression ($\mathcal{C}$-BALD). We propose a novel modelling approach to estimate the $\mathcal{C}$-BALD objective and use it for active learning in the censored setting. Across a wide range of datasets and models, we demonstrate that $\mathcal{C}$-BALD outperforms other Bayesian active learning methods in censored regression. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.11973v1-abstract-full').style.display = 'none'; document.getElementById('2402.11973v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07799">arXiv:2402.07799</a> <span> [<a href="https://arxiv.org/pdf/2402.07799">pdf</a>, <a href="https://arxiv.org/format/2402.07799">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"> Generalising Planning Environment Redesign </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pozanco%2C+A">Alberto Pozanco</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+R+F">Ramon Fraga Pereira</a>, <a href="/search/cs?searchtype=author&query=Borrajo%2C+D">Daniel Borrajo</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="2402.07799v2-abstract-short" style="display: inline;"> In Environment Design, one interested party seeks to affect another agent's decisions by applying changes to the environment. Most research on planning environment (re)design assumes the interested party's objective is to facilitate the recognition of goals and plans, and search over the space of environment modifications to find the minimal set of changes that simplify those tasks and optimise a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07799v2-abstract-full').style.display = 'inline'; document.getElementById('2402.07799v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07799v2-abstract-full" style="display: none;"> In Environment Design, one interested party seeks to affect another agent's decisions by applying changes to the environment. Most research on planning environment (re)design assumes the interested party's objective is to facilitate the recognition of goals and plans, and search over the space of environment modifications to find the minimal set of changes that simplify those tasks and optimise a particular metric. This search space is usually intractable, so existing approaches devise metric-dependent pruning techniques for performing search more efficiently. This results in approaches that are not able to generalise across different objectives and/or metrics. In this paper, we argue that the interested party could have objectives and metrics that are not necessarily related to recognising agents' goals or plans. Thus, to generalise the task of Planning Environment Redesign, we develop a general environment redesign approach that is metric-agnostic and leverages recent research on top-quality planning to efficiently redesign planning environments according to any interested party's objective and metric. Experiments over a set of environment redesign benchmarks show that our general approach outperforms existing approaches when using well-known metrics, such as facilitating the recognition of goals, as well as its effectiveness when solving environment redesign tasks that optimise a novel set of different metrics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07799v2-abstract-full').style.display = 'none'; document.getElementById('2402.07799v2-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">Paper accepted at AAAI'24</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.07583">arXiv:2401.07583</a> <span> [<a href="https://arxiv.org/pdf/2401.07583">pdf</a>, <a href="https://arxiv.org/format/2401.07583">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Small Quantum Codes from Algebraic Extensions of Generalized Bicycle Codes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Koukoulekidis%2C+N">Nikolaos Koukoulekidis</a>, <a href="/search/cs?searchtype=author&query=%C5%A0imkovic%2C+F">Fedor 艩imkovic IV</a>, <a href="/search/cs?searchtype=author&query=Leib%2C+M">Martin Leib</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+R+F">Francisco Revson Fernandes Pereira</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="2401.07583v1-abstract-short" style="display: inline;"> Quantum error correction is rapidly seeing first experimental implementations, but there is a significant gap between asymptotically optimal error-correcting codes and codes that are experimentally feasible. Quantum LDPC codes range from the surface code, which has a vanishing encoding rate, to very promising codes with constant encoding rate and linear distance. In this work, motivated by current… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.07583v1-abstract-full').style.display = 'inline'; document.getElementById('2401.07583v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.07583v1-abstract-full" style="display: none;"> Quantum error correction is rapidly seeing first experimental implementations, but there is a significant gap between asymptotically optimal error-correcting codes and codes that are experimentally feasible. Quantum LDPC codes range from the surface code, which has a vanishing encoding rate, to very promising codes with constant encoding rate and linear distance. In this work, motivated by current small-scale experimental quantum processing units, we devise small quantum codes that are inspired by a subset of quantum LDPC codes, known as generalized bicycle (GB) codes. We introduce a code construction based on algebraic manipulation of the parity-check matrix of GB codes, rather than manipulation of Tanner graphs. Our construction leads to families of quantum LDPC codes of small size, and we demonstrate numerically that their performance scales comparably to the performance of surface codes for similar sizes under a phenomenological noise model. The advantage of our code family is that they encode many logical qubits in one code, at the expense of non-local connectivity. We then explore three variants of the code construction focusing on reducing the long-range connectivity by bringing it closer to the current experimental capabilities of short-range connectivity devices. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.07583v1-abstract-full').style.display = 'none'; document.getElementById('2401.07583v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.07762">arXiv:2312.07762</a> <span> [<a href="https://arxiv.org/pdf/2312.07762">pdf</a>, <a href="https://arxiv.org/format/2312.07762">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="Numerical Analysis">math.NA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Interpretable factorization of clinical questionnaires to identify latent factors of psychopathology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lam%2C+K+C">Ka Chun Lam</a>, <a href="/search/cs?searchtype=author&query=Mahony%2C+B+W">Bridget W Mahony</a>, <a href="/search/cs?searchtype=author&query=Raznahan%2C+A">Armin Raznahan</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</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="2312.07762v1-abstract-short" style="display: inline;"> Psychiatry research seeks to understand the manifestations of psychopathology in behavior, as measured in questionnaire data, by identifying a small number of latent factors that explain them. While factor analysis is the traditional tool for this purpose, the resulting factors may not be interpretable, and may also be subject to confounding variables. Moreover, missing data are common, and explic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.07762v1-abstract-full').style.display = 'inline'; document.getElementById('2312.07762v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.07762v1-abstract-full" style="display: none;"> Psychiatry research seeks to understand the manifestations of psychopathology in behavior, as measured in questionnaire data, by identifying a small number of latent factors that explain them. While factor analysis is the traditional tool for this purpose, the resulting factors may not be interpretable, and may also be subject to confounding variables. Moreover, missing data are common, and explicit imputation is often required. To overcome these limitations, we introduce interpretability constrained questionnaire factorization (ICQF), a non-negative matrix factorization method with regularization tailored for questionnaire data. Our method aims to promote factor interpretability and solution stability. We provide an optimization procedure with theoretical convergence guarantees, and an automated procedure to detect latent dimensionality accurately. We validate these procedures using realistic synthetic data. We demonstrate the effectiveness of our method in a widely used general-purpose questionnaire, in two independent datasets (the Healthy Brain Network and Adolescent Brain Cognitive Development studies). Specifically, we show that ICQF improves interpretability, as defined by domain experts, while preserving diagnostic information across a range of disorders, and outperforms competing methods for smaller dataset sizes. This suggests that the regularization in our method matches domain characteristics. The python implementation for ICQF is available at \url{https://github.com/jefferykclam/ICQF}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.07762v1-abstract-full').style.display = 'none'; document.getElementById('2312.07762v1-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 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">MSC Class:</span> 68 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> G.1.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.00507">arXiv:2312.00507</a> <span> [<a href="https://arxiv.org/pdf/2312.00507">pdf</a>, <a href="https://arxiv.org/format/2312.00507">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Programming Languages">cs.PL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> VEXIR2Vec: An Architecture-Neutral Embedding Framework for Binary Similarity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=VenkataKeerthy%2C+S">S. VenkataKeerthy</a>, <a href="/search/cs?searchtype=author&query=Banerjee%2C+S">Soumya Banerjee</a>, <a href="/search/cs?searchtype=author&query=Dey%2C+S">Sayan Dey</a>, <a href="/search/cs?searchtype=author&query=Andaluri%2C+Y">Yashas Andaluri</a>, <a href="/search/cs?searchtype=author&query=PS%2C+R">Raghul PS</a>, <a href="/search/cs?searchtype=author&query=Kalyanasundaram%2C+S">Subrahmanyam Kalyanasundaram</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+M+Q">Fernando Magno Quint茫o Pereira</a>, <a href="/search/cs?searchtype=author&query=Upadrasta%2C+R">Ramakrishna Upadrasta</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="2312.00507v2-abstract-short" style="display: inline;"> Binary similarity involves determining whether two binary programs exhibit similar functionality, often originating from the same source code. In this work, we propose VexIR2Vec, an approach for binary similarity using VEX-IR, an architecture-neutral Intermediate Representation (IR). We extract the embeddings from sequences of basic blocks, termed peepholes, derived by random walks on the control-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.00507v2-abstract-full').style.display = 'inline'; document.getElementById('2312.00507v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.00507v2-abstract-full" style="display: none;"> Binary similarity involves determining whether two binary programs exhibit similar functionality, often originating from the same source code. In this work, we propose VexIR2Vec, an approach for binary similarity using VEX-IR, an architecture-neutral Intermediate Representation (IR). We extract the embeddings from sequences of basic blocks, termed peepholes, derived by random walks on the control-flow graph. The peepholes are normalized using transformations inspired by compiler optimizations. The VEX-IR Normalization Engine mitigates, with these transformations, the architectural and compiler-induced variations in binaries while exposing semantic similarities. We then learn the vocabulary of representations at the entity level of the IR using the knowledge graph embedding techniques in an unsupervised manner. This vocabulary is used to derive function embeddings for similarity assessment using VexNet, a feed-forward Siamese network designed to position similar functions closely and separate dissimilar ones in an n-dimensional space. This approach is amenable for both diffing and searching tasks, ensuring robustness against Out-Of-Vocabulary (OOV) issues. We evaluate VexIR2Vec on a dataset comprising 2.7M functions and 15.5K binaries from 7 projects compiled across 12 compilers targeting x86 and ARM architectures. In diffing experiments, VexIR2Vec outperforms the nearest baselines by $40\%$, $18\%$, $21\%$, and $60\%$ in cross-optimization, cross-compilation, cross-architecture, and obfuscation settings, respectively. In the searching experiment, VexIR2Vec achieves a mean average precision of $0.76$, outperforming the nearest baseline by $46\%$. Our framework is highly scalable and is built as a lightweight, multi-threaded, parallel library using only open-source tools. VexIR2Vec is $3.1$-$3.5 \times$ faster than the closest baselines and orders-of-magnitude faster than other tools. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.00507v2-abstract-full').style.display = 'none'; document.getElementById('2312.00507v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 December, 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/2310.18849">arXiv:2310.18849</a> <span> [<a href="https://arxiv.org/pdf/2310.18849">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning-based Compressed Domain Multimedia for Man and Machine: A Taxonomy and Application to Point Cloud Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Seleem%2C+A">Abdelrahman Seleem</a>, <a href="/search/cs?searchtype=author&query=Guarda%2C+A+F+R">Andr茅 F. R. Guarda</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+N+M+M">Nuno M. M. Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Fernando Pereira</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="2310.18849v2-abstract-short" style="display: inline;"> In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, deep learning plays a undamental role in extracting features from the multimedia representation data, usually producing a compressed representation referred to as latent representation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18849v2-abstract-full').style.display = 'inline'; document.getElementById('2310.18849v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.18849v2-abstract-full" style="display: none;"> In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, deep learning plays a undamental role in extracting features from the multimedia representation data, usually producing a compressed representation referred to as latent representation. The increasing development and adoption of deep learning-based solutions in a wide area of multimedia applications have opened an exciting new vision where a common compressed multimedia representation is used for both man and machine. The main benefits of this vision are two-fold: i) improved performance for the computer vision tasks, since the effects of coding artifacts are mitigated; and ii) reduced computational complexity, since prior decoding is not required. This paper proposes the first taxonomy for designing compressed domain computer vision solutions driven by the architecture and weights compatibility with an available spatio-temporal computer vision processor. The potential of the proposed taxonomy is demonstrated for the specific case of point cloud classification by designing novel compressed domain processors using the JPEG Pleno Point Cloud Coding standard under development and adaptations of the PointGrid classifier. Experimental results show that the designed compressed domain point cloud classification solutions can significantly outperform the spatial-temporal domain classification benchmarks when applied to the decompressed data, containing coding artifacts, and even surpass their performance when applied to the original uncompressed data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18849v2-abstract-full').style.display = 'none'; document.getElementById('2310.18849v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.12332">arXiv:2309.12332</a> <span> [<a href="https://arxiv.org/pdf/2309.12332">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</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"> Education in the age of Generative AI: Context and Recent Developments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mello%2C+R+F">Rafael Ferreira Mello</a>, <a href="/search/cs?searchtype=author&query=Freitas%2C+E">Elyda Freitas</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+D">Filipe Dwan Pereira</a>, <a href="/search/cs?searchtype=author&query=Cabral%2C+L">Luciano Cabral</a>, <a href="/search/cs?searchtype=author&query=Tedesco%2C+P">Patricia Tedesco</a>, <a href="/search/cs?searchtype=author&query=Ramalho%2C+G">Geber Ramalho</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="2309.12332v1-abstract-short" style="display: inline;"> With the emergence of generative artificial intelligence, an increasing number of individuals and organizations have begun exploring its potential to enhance productivity and improve product quality across various sectors. The field of education is no exception. However, it is vital to notice that artificial intelligence adoption in education dates back to the 1960s. In light of this historical co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.12332v1-abstract-full').style.display = 'inline'; document.getElementById('2309.12332v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.12332v1-abstract-full" style="display: none;"> With the emergence of generative artificial intelligence, an increasing number of individuals and organizations have begun exploring its potential to enhance productivity and improve product quality across various sectors. The field of education is no exception. However, it is vital to notice that artificial intelligence adoption in education dates back to the 1960s. In light of this historical context, this white paper serves as the inaugural piece in a four-part series that elucidates the role of AI in education. The series delves into topics such as its potential, successful applications, limitations, ethical considerations, and future trends. This initial article provides a comprehensive overview of the field, highlighting the recent developments within the generative artificial intelligence sphere. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.12332v1-abstract-full').style.display = 'none'; document.getElementById('2309.12332v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.14122">arXiv:2308.14122</a> <span> [<a href="https://arxiv.org/pdf/2308.14122">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> </div> <p class="title is-5 mathjax"> Preparing Reproducible Scientific Artifacts using Docker </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Canesche%2C+M">Michael Canesche</a>, <a href="/search/cs?searchtype=author&query=Leissa%2C+R">Roland Leissa</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+M+Q">Fernando Magno Quint茫o Pereira</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="2308.14122v1-abstract-short" style="display: inline;"> The pursuit of scientific knowledge strongly depends on the ability to reproduce and validate research results. It is a well-known fact that the scientific community faces challenges related to transparency, reliability, and the reproducibility of empirical published results. Consequently, the design and preparation of reproducible artifacts has a fundamental role in the development of science. Re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.14122v1-abstract-full').style.display = 'inline'; document.getElementById('2308.14122v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.14122v1-abstract-full" style="display: none;"> The pursuit of scientific knowledge strongly depends on the ability to reproduce and validate research results. It is a well-known fact that the scientific community faces challenges related to transparency, reliability, and the reproducibility of empirical published results. Consequently, the design and preparation of reproducible artifacts has a fundamental role in the development of science. Reproducible artifacts comprise comprehensive documentation, data, and code that enable replication and validation of research findings by others. In this work, we discuss a methodology to construct reproducible artifacts based on Docker. Our presentation centers around the preparation of an artifact to be submitted to scientific venues that encourage or require this process. This report's primary audience are scientists working with empirical computer science; however, we believe that the presented methodology can be extended to other technology-oriented empirical disciplines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.14122v1-abstract-full').style.display = 'none'; document.getElementById('2308.14122v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages. Manuscript not submitted to any conference, used as a guideline for authors who want to submit artifacts to artifact evaluation pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.10650">arXiv:2308.10650</a> <span> [<a href="https://arxiv.org/pdf/2308.10650">pdf</a>, <a href="https://arxiv.org/format/2308.10650">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="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Deep Evidential Learning for Bayesian Quantile Regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=H%C3%BCttel%2C+F+B">Frederik Boe H眉ttel</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+F">Filipe Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C芒mara Pereira</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="2308.10650v1-abstract-short" style="display: inline;"> It is desirable to have accurate uncertainty estimation from a single deterministic forward-pass model, as traditional methods for uncertainty quantification are computationally expensive. However, this is difficult because single forward-pass models do not sample weights during inference and often make assumptions about the target distribution, such as assuming it is Gaussian. This can be restric… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.10650v1-abstract-full').style.display = 'inline'; document.getElementById('2308.10650v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.10650v1-abstract-full" style="display: none;"> It is desirable to have accurate uncertainty estimation from a single deterministic forward-pass model, as traditional methods for uncertainty quantification are computationally expensive. However, this is difficult because single forward-pass models do not sample weights during inference and often make assumptions about the target distribution, such as assuming it is Gaussian. This can be restrictive in regression tasks, where the mean and standard deviation are inadequate to model the target distribution accurately. This paper proposes a deep Bayesian quantile regression model that can estimate the quantiles of a continuous target distribution without the Gaussian assumption. The proposed method is based on evidential learning, which allows the model to capture aleatoric and epistemic uncertainty with a single deterministic forward-pass model. This makes the method efficient and scalable to large models and datasets. We demonstrate that the proposed method achieves calibrated uncertainties on non-Gaussian distributions, disentanglement of aleatoric and epistemic uncertainty, and robustness to out-of-distribution samples. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.10650v1-abstract-full').style.display = 'none'; document.getElementById('2308.10650v1-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 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/2308.03404">arXiv:2308.03404</a> <span> [<a href="https://arxiv.org/pdf/2308.03404">pdf</a>, <a href="https://arxiv.org/format/2308.03404">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"> Applied metamodelling for ATM performance simulations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Riis%2C+C">Christoffer Riis</a>, <a href="/search/cs?searchtype=author&query=Antunes%2C+F+N">Francisco N. Antunes</a>, <a href="/search/cs?searchtype=author&query=Boli%C4%87%2C+T">Tatjana Boli膰</a>, <a href="/search/cs?searchtype=author&query=Gurtner%2C+G">G茅rald Gurtner</a>, <a href="/search/cs?searchtype=author&query=Cook%2C+A">Andrew Cook</a>, <a href="/search/cs?searchtype=author&query=Azevedo%2C+C+L">Carlos Lima Azevedo</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C芒mara Pereira</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="2308.03404v1-abstract-short" style="display: inline;"> The use of Air traffic management (ATM) simulators for planing and operations can be challenging due to their modelling complexity. This paper presents XALM (eXplainable Active Learning Metamodel), a three-step framework integrating active learning and SHAP (SHapley Additive exPlanations) values into simulation metamodels for supporting ATM decision-making. XALM efficiently uncovers hidden relatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03404v1-abstract-full').style.display = 'inline'; document.getElementById('2308.03404v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.03404v1-abstract-full" style="display: none;"> The use of Air traffic management (ATM) simulators for planing and operations can be challenging due to their modelling complexity. This paper presents XALM (eXplainable Active Learning Metamodel), a three-step framework integrating active learning and SHAP (SHapley Additive exPlanations) values into simulation metamodels for supporting ATM decision-making. XALM efficiently uncovers hidden relationships among input and output variables in ATM simulators, those usually of interest in policy analysis. Our experiments show XALM's predictive performance comparable to the XGBoost metamodel with fewer simulations. Additionally, XALM exhibits superior explanatory capabilities compared to non-active learning metamodels. Using the `Mercury' (flight and passenger) ATM simulator, XALM is applied to a real-world scenario in Paris Charles de Gaulle airport, extending an arrival manager's range and scope by analysing six variables. This case study illustrates XALM's effectiveness in enhancing simulation interpretability and understanding variable interactions. By addressing computational challenges and improving explainability, XALM complements traditional simulation-based analyses. Lastly, we discuss two practical approaches for reducing the computational burden of the metamodelling further: we introduce a stopping criterion for active learning based on the inherent uncertainty of the metamodel, and we show how the simulations used for the metamodel can be reused across key performance indicators, thus decreasing the overall number of simulations needed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03404v1-abstract-full').style.display = 'none'; document.getElementById('2308.03404v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 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/2307.14791">arXiv:2307.14791</a> <span> [<a href="https://arxiv.org/pdf/2307.14791">pdf</a>, <a href="https://arxiv.org/format/2307.14791">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> <p class="title is-5 mathjax"> Automatic Parallelization of Software Network Functions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</a>, <a href="/search/cs?searchtype=author&query=Ramos%2C+F+M+V">Fernando M. V. Ramos</a>, <a href="/search/cs?searchtype=author&query=Pedrosa%2C+L">Luis Pedrosa</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="2307.14791v2-abstract-short" style="display: inline;"> Software network functions (NFs) trade-off flexibility and ease of deployment for an increased challenge of performance. The traditional way to increase NF performance is by distributing traffic to multiple CPU cores, but this poses a significant challenge: how to parallelize an NF without breaking its semantics? We propose Maestro, a tool that analyzes a sequential implementation of an NF and aut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.14791v2-abstract-full').style.display = 'inline'; document.getElementById('2307.14791v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.14791v2-abstract-full" style="display: none;"> Software network functions (NFs) trade-off flexibility and ease of deployment for an increased challenge of performance. The traditional way to increase NF performance is by distributing traffic to multiple CPU cores, but this poses a significant challenge: how to parallelize an NF without breaking its semantics? We propose Maestro, a tool that analyzes a sequential implementation of an NF and automatically generates an enhanced parallel version that carefully configures the NIC's Receive Side Scaling mechanism to distribute traffic across cores, while preserving semantics. When possible, Maestro orchestrates a shared-nothing architecture, with each core operating independently without shared memory coordination, maximizing performance. Otherwise, Maestro choreographs a fine-grained read-write locking mechanism that optimizes operation for typical Internet traffic. We parallelized 8 software NFs and show that they generally scale-up linearly until bottlenecked by PCIe when using small packets or by 100Gbps line-rate with typical Internet traffic. Maestro further outperforms modern hardware-based transactional memory mechanisms, even for challenging parallel-unfriendly workloads. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.14791v2-abstract-full').style.display = 'none'; document.getElementById('2307.14791v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 July, 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">21 pages, 14 figures, to be published in NSDI24</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.10892">arXiv:2307.10892</a> <span> [<a href="https://arxiv.org/pdf/2307.10892">pdf</a>, <a href="https://arxiv.org/format/2307.10892">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"> Learning and Generalizing Polynomials in Simulation Metamodeling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hauch%2C+J">Jesper Hauch</a>, <a href="/search/cs?searchtype=author&query=Riis%2C+C">Christoffer Riis</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C. Pereira</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="2307.10892v1-abstract-short" style="display: inline;"> The ability to learn polynomials and generalize out-of-distribution is essential for simulation metamodels in many disciplines of engineering, where the time step updates are described by polynomials. While feed forward neural networks can fit any function, they cannot generalize out-of-distribution for higher-order polynomials. Therefore, this paper collects and proposes multiplicative neural net… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10892v1-abstract-full').style.display = 'inline'; document.getElementById('2307.10892v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.10892v1-abstract-full" style="display: none;"> The ability to learn polynomials and generalize out-of-distribution is essential for simulation metamodels in many disciplines of engineering, where the time step updates are described by polynomials. While feed forward neural networks can fit any function, they cannot generalize out-of-distribution for higher-order polynomials. Therefore, this paper collects and proposes multiplicative neural network (MNN) architectures that are used as recursive building blocks for approximating higher-order polynomials. Our experiments show that MNNs are better than baseline models at generalizing, and their performance in validation is true to their performance in out-of-distribution tests. In addition to MNN architectures, a simulation metamodeling approach is proposed for simulations with polynomial time step updates. For these simulations, simulating a time interval can be performed in fewer steps by increasing the step size, which entails approximating higher-order polynomials. While our approach is compatible with any simulation with polynomial time step updates, a demonstration is shown for an epidemiology simulation model, which also shows the inductive bias in MNNs for learning and generalizing higher-order polynomials. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10892v1-abstract-full').style.display = 'none'; document.getElementById('2307.10892v1-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.08680">arXiv:2306.08680</a> <span> [<a href="https://arxiv.org/pdf/2306.08680">pdf</a>, <a href="https://arxiv.org/format/2306.08680">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"> Temporally Extended Goal Recognition in Fully Observable Non-Deterministic Domain Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pereira%2C+R+F">Ramon Fraga Pereira</a>, <a href="/search/cs?searchtype=author&query=Fuggitti%2C+F">Francesco Fuggitti</a>, <a href="/search/cs?searchtype=author&query=Meneguzzi%2C+F">Felipe Meneguzzi</a>, <a href="/search/cs?searchtype=author&query=De+Giacomo%2C+G">Giuseppe De Giacomo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.08680v1-abstract-short" style="display: inline;"> Goal Recognition is the task of discerning the correct intended goal that an agent aims to achieve, given a set of goal hypotheses, a domain model, and a sequence of observations (i.e., a sample of the plan executed in the environment). Existing approaches assume that goal hypotheses comprise a single conjunctive formula over a single final state and that the environment dynamics are deterministic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.08680v1-abstract-full').style.display = 'inline'; document.getElementById('2306.08680v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.08680v1-abstract-full" style="display: none;"> Goal Recognition is the task of discerning the correct intended goal that an agent aims to achieve, given a set of goal hypotheses, a domain model, and a sequence of observations (i.e., a sample of the plan executed in the environment). Existing approaches assume that goal hypotheses comprise a single conjunctive formula over a single final state and that the environment dynamics are deterministic, preventing the recognition of temporally extended goals in more complex settings. In this paper, we expand goal recognition to temporally extended goals in Fully Observable Non-Deterministic (FOND) planning domain models, focusing on goals on finite traces expressed in Linear Temporal Logic (LTLf) and Pure Past Linear Temporal Logic (PLTLf). We develop the first approach capable of recognizing goals in such settings and evaluate it using different LTLf and PLTLf goals over six FOND planning domain models. Empirical results show that our approach is accurate in recognizing temporally extended goals in different recognition settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.08680v1-abstract-full').style.display = 'none'; document.getElementById('2306.08680v1-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: substantial text overlap with arXiv:2103.11692</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.09129">arXiv:2305.09129</a> <span> [<a href="https://arxiv.org/pdf/2305.09129">pdf</a>, <a href="https://arxiv.org/format/2305.09129">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> Graph Reinforcement Learning for Network Control via Bi-Level Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gammelli%2C+D">Daniele Gammelli</a>, <a href="/search/cs?searchtype=author&query=Harrison%2C+J">James Harrison</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+K">Kaidi Yang</a>, <a href="/search/cs?searchtype=author&query=Pavone%2C+M">Marco Pavone</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+F">Filipe Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C. Pereira</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="2305.09129v1-abstract-short" style="display: inline;"> Optimization problems over dynamic networks have been extensively studied and widely used in the past decades to formulate numerous real-world problems. However, (1) traditional optimization-based approaches do not scale to large networks, and (2) the design of good heuristics or approximation algorithms often requires significant manual trial-and-error. In this work, we argue that data-driven str… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.09129v1-abstract-full').style.display = 'inline'; document.getElementById('2305.09129v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.09129v1-abstract-full" style="display: none;"> Optimization problems over dynamic networks have been extensively studied and widely used in the past decades to formulate numerous real-world problems. However, (1) traditional optimization-based approaches do not scale to large networks, and (2) the design of good heuristics or approximation algorithms often requires significant manual trial-and-error. In this work, we argue that data-driven strategies can automate this process and learn efficient algorithms without compromising optimality. To do so, we present network control problems through the lens of reinforcement learning and propose a graph network-based framework to handle a broad class of problems. Instead of naively computing actions over high-dimensional graph elements, e.g., edges, we propose a bi-level formulation where we (1) specify a desired next state via RL, and (2) solve a convex program to best achieve it, leading to drastically improved scalability and performance. We further highlight a collection of desirable features to system designers, investigate design decisions, and present experiments on real-world control problems showing the utility, scalability, and flexibility of our framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.09129v1-abstract-full').style.display = 'none'; document.getElementById('2305.09129v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">9 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.01424">arXiv:2305.01424</a> <span> [<a href="https://arxiv.org/pdf/2305.01424">pdf</a>, <a href="https://arxiv.org/format/2305.01424">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="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> Uncertain Machine Ethical Decisions Using Hypothetical Retrospection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kolker%2C+S">Simon Kolker</a>, <a href="/search/cs?searchtype=author&query=Dennis%2C+L">Louise Dennis</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+R+F">Ramon Fraga Pereira</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+M">Mengwei Xu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.01424v2-abstract-short" style="display: inline;"> We propose the use of the hypothetical retrospection argumentation procedure, developed by Sven Ove Hansson to improve existing approaches to machine ethical reasoning by accounting for probability and uncertainty from a position of Philosophy that resonates with humans. Actions are represented with a branching set of potential outcomes, each with a state, utility, and either a numeric or poetic p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.01424v2-abstract-full').style.display = 'inline'; document.getElementById('2305.01424v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.01424v2-abstract-full" style="display: none;"> We propose the use of the hypothetical retrospection argumentation procedure, developed by Sven Ove Hansson to improve existing approaches to machine ethical reasoning by accounting for probability and uncertainty from a position of Philosophy that resonates with humans. Actions are represented with a branching set of potential outcomes, each with a state, utility, and either a numeric or poetic probability estimate. Actions are chosen based on comparisons between sets of arguments favouring actions from the perspective of their branches, even those branches that led to an undesirable outcome. This use of arguments allows a variety of philosophical theories for ethical reasoning to be used, potentially in flexible combination with each other. We implement the procedure, applying consequentialist and deontological ethical theories, independently and concurrently, to an autonomous library system use case. We introduce a preliminary framework that seems to meet the varied requirements of a machine ethics system: versatility under multiple theories and a resonance with humans that enables transparency and explainability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.01424v2-abstract-full').style.display = 'none'; document.getElementById('2305.01424v2-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 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.14833">arXiv:2302.14833</a> <span> [<a href="https://arxiv.org/pdf/2302.14833">pdf</a>, <a href="https://arxiv.org/format/2302.14833">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Schmidt%2C+C">Carolin Schmidt</a>, <a href="/search/cs?searchtype=author&query=Gammelli%2C+D">Daniele Gammelli</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco Camara Pereira</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+F">Filipe Rodrigues</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="2302.14833v2-abstract-short" style="display: inline;"> Autonomous Mobility-on-Demand (AMoD) systems are an evolving mode of transportation in which a centrally coordinated fleet of self-driving vehicles dynamically serves travel requests. The control of these systems is typically formulated as a large network optimization problem, and reinforcement learning (RL) has recently emerged as a promising approach to solve the open challenges in this space. R… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.14833v2-abstract-full').style.display = 'inline'; document.getElementById('2302.14833v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.14833v2-abstract-full" style="display: none;"> Autonomous Mobility-on-Demand (AMoD) systems are an evolving mode of transportation in which a centrally coordinated fleet of self-driving vehicles dynamically serves travel requests. The control of these systems is typically formulated as a large network optimization problem, and reinforcement learning (RL) has recently emerged as a promising approach to solve the open challenges in this space. Recent centralized RL approaches focus on learning from online data, ignoring the per-sample-cost of interactions within real-world transportation systems. To address these limitations, we propose to formalize the control of AMoD systems through the lens of offline reinforcement learning and learn effective control strategies using solely offline data, which is readily available to current mobility operators. We further investigate design decisions and provide empirical evidence based on data from real-world mobility systems showing how offline learning allows to recover AMoD control policies that (i) exhibit performance on par with online methods, (ii) allow for sample-efficient online fine-tuning and (iii) eliminate the need for complex simulation environments. Crucially, this paper demonstrates that offline RL is a promising paradigm for the application of RL-based solutions within economically-critical systems, such as mobility systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.14833v2-abstract-full').style.display = 'none'; document.getElementById('2302.14833v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.09871">arXiv:2302.09871</a> <span> [<a href="https://arxiv.org/pdf/2302.09871">pdf</a>, <a href="https://arxiv.org/format/2302.09871">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Econometrics">econ.EM</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"> Attitudes and Latent Class Choice Models using Machine learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lahoz%2C+L+T">Lorena Torres Lahoz</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco Camara Pereira</a>, <a href="/search/cs?searchtype=author&query=Sfeir%2C+G">Georges Sfeir</a>, <a href="/search/cs?searchtype=author&query=Arkoudi%2C+I">Ioanna Arkoudi</a>, <a href="/search/cs?searchtype=author&query=Monteiro%2C+M+M">Mayara Moraes Monteiro</a>, <a href="/search/cs?searchtype=author&query=Azevedo%2C+C+L">Carlos Lima Azevedo</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="2302.09871v1-abstract-short" style="display: inline;"> Latent Class Choice Models (LCCM) are extensions of discrete choice models (DCMs) that capture unobserved heterogeneity in the choice process by segmenting the population based on the assumption of preference similarities. We present a method of efficiently incorporating attitudinal indicators in the specification of LCCM, by introducing Artificial Neural Networks (ANN) to formulate latent variabl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.09871v1-abstract-full').style.display = 'inline'; document.getElementById('2302.09871v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.09871v1-abstract-full" style="display: none;"> Latent Class Choice Models (LCCM) are extensions of discrete choice models (DCMs) that capture unobserved heterogeneity in the choice process by segmenting the population based on the assumption of preference similarities. We present a method of efficiently incorporating attitudinal indicators in the specification of LCCM, by introducing Artificial Neural Networks (ANN) to formulate latent variables constructs. This formulation overcomes structural equations in its capability of exploring the relationship between the attitudinal indicators and the decision choice, given the Machine Learning (ML) flexibility and power in capturing unobserved and complex behavioural features, such as attitudes and beliefs. All of this while still maintaining the consistency of the theoretical assumptions presented in the Generalized Random Utility model and the interpretability of the estimated parameters. We test our proposed framework for estimating a Car-Sharing (CS) service subscription choice with stated preference data from Copenhagen, Denmark. The results show that our proposed approach provides a complete and realistic segmentation, which helps design better policies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.09871v1-abstract-full').style.display = 'none'; document.getElementById('2302.09871v1-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, 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">25 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.11489">arXiv:2301.11489</a> <span> [<a href="https://arxiv.org/pdf/2301.11489">pdf</a>, <a href="https://arxiv.org/format/2301.11489">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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"> Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Leszczynski%2C+M">Megan Leszczynski</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shu Zhang</a>, <a href="/search/cs?searchtype=author&query=Ganti%2C+R">Ravi Ganti</a>, <a href="/search/cs?searchtype=author&query=Balog%2C+K">Krisztian Balog</a>, <a href="/search/cs?searchtype=author&query=Radlinski%2C+F">Filip Radlinski</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Fernando Pereira</a>, <a href="/search/cs?searchtype=author&query=Chaganty%2C+A+T">Arun Tejasvi Chaganty</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.11489v3-abstract-short" style="display: inline;"> Recommender systems are ubiquitous yet often difficult for users to control, and adjust if recommendation quality is poor. This has motivated conversational recommender systems (CRSs), with control provided through natural language feedback. However, as with most application domains, building robust CRSs requires training data that reflects system usage$\unicode{x2014}$here conversations with user… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.11489v3-abstract-full').style.display = 'inline'; document.getElementById('2301.11489v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.11489v3-abstract-full" style="display: none;"> Recommender systems are ubiquitous yet often difficult for users to control, and adjust if recommendation quality is poor. This has motivated conversational recommender systems (CRSs), with control provided through natural language feedback. However, as with most application domains, building robust CRSs requires training data that reflects system usage$\unicode{x2014}$here conversations with user utterances paired with items that cover a wide range of preferences. This has proved challenging to collect scalably using conventional methods. We address the question of whether it can be generated synthetically, building on recent advances in natural language. We evaluate in the setting of item set recommendation, noting the increasing attention to this task motivated by use cases like music, news, and recipe recommendation. We present TalkTheWalk, which synthesizes realistic high-quality conversational data by leveraging domain expertise encoded in widely available curated item collections, generating a sequence of hypothetical yet plausible item sets, then using a language model to produce corresponding user utterances. We generate over one million diverse playlist curation conversations in the music domain, and show these contain consistent utterances with relevant item sets nearly matching the quality of an existing but small human-collected dataset for this task. We demonstrate the utility of the generated synthetic dataset on a conversational item retrieval task and show that it improves over both unsupervised baselines and systems trained on a real dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.11489v3-abstract-full').style.display = 'none'; document.getElementById('2301.11489v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.06418">arXiv:2301.06418</a> <span> [<a href="https://arxiv.org/pdf/2301.06418">pdf</a>, <a href="https://arxiv.org/format/2301.06418">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Mind the Gap: Modelling Difference Between Censored and Uncensored Electric Vehicle Charging Demand </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=H%C3%BCttel%2C+F+B">Frederik Boe H眉ttel</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+F">Filipe Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C芒mara Pereira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.06418v4-abstract-short" style="display: inline;"> Electric vehicle charging demand models, with charging records as input, will inherently be biased toward the supply of available chargers. These models often fail to account for demand lost from occupied charging stations and competitors. The lost demand suggests that the actual demand is likely higher than the charging records reflect, i.e., the true demand is latent (unobserved), and the observ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06418v4-abstract-full').style.display = 'inline'; document.getElementById('2301.06418v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.06418v4-abstract-full" style="display: none;"> Electric vehicle charging demand models, with charging records as input, will inherently be biased toward the supply of available chargers. These models often fail to account for demand lost from occupied charging stations and competitors. The lost demand suggests that the actual demand is likely higher than the charging records reflect, i.e., the true demand is latent (unobserved), and the observations are censored. As a result, machine learning models that rely on these observed records for forecasting charging demand may be limited in their application in future infrastructure expansion and supply management, as they do not estimate the true demand for charging. We propose using censorship-aware models to model charging demand to address this limitation. These models incorporate censorship in their loss functions and learn the true latent demand distribution from observed charging records. We study how occupied charging stations and competing services censor demand using GPS trajectories from cars in Copenhagen, Denmark. We find that censorship occurs up to $61\%$ of the time in some areas of the city. We use the observed charging demand from our study to estimate the true demand and find that censorship-aware models provide better prediction and uncertainty estimation of actual demand than censorship-unaware models. We suggest that future charging models based on charging records should account for censoring to expand the application areas of machine learning models in supply management and infrastructure expansion. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.06418v4-abstract-full').style.display = 'none'; document.getElementById('2301.06418v4-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.09295">arXiv:2211.09295</a> <span> [<a href="https://arxiv.org/pdf/2211.09295">pdf</a>, <a href="https://arxiv.org/format/2211.09295">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">stat.ML</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"> Testing for context-dependent changes in neural encoding in naturalistic experiments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yenho Chen</a>, <a href="/search/cs?searchtype=author&query=Harris%2C+C+W">Carl W. Harris</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+X">Xiaoyu Ma</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zheng Li</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+C+Y">Charles Y. Zheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2211.09295v1-abstract-short" style="display: inline;"> We propose a decoding-based approach to detect context effects on neural codes in longitudinal neural recording data. The approach is agnostic to how information is encoded in neural activity, and can control for a variety of possible confounding factors present in the data. We demonstrate our approach by determining whether it is possible to decode location encoding from prefrontal cortex in the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.09295v1-abstract-full').style.display = 'inline'; document.getElementById('2211.09295v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.09295v1-abstract-full" style="display: none;"> We propose a decoding-based approach to detect context effects on neural codes in longitudinal neural recording data. The approach is agnostic to how information is encoded in neural activity, and can control for a variety of possible confounding factors present in the data. We demonstrate our approach by determining whether it is possible to decode location encoding from prefrontal cortex in the mouse and, further, testing whether the encoding changes due to task engagement. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.09295v1-abstract-full').style.display = 'none'; document.getElementById('2211.09295v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">39 pages, 13 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/2208.04667">arXiv:2208.04667</a> <span> [<a href="https://arxiv.org/pdf/2208.04667">pdf</a>, <a href="https://arxiv.org/format/2208.04667">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">stat.ML</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"> Representation learning of rare temporal conditions for travel time prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Petersen%2C+N">Niklas Petersen</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+F">Filipe Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</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="2208.04667v1-abstract-short" style="display: inline;"> Predicting travel time under rare temporal conditions (e.g., public holidays, school vacation period, etc.) constitutes a challenge due to the limitation of historical data. If at all available, historical data often form a heterogeneous time series due to high probability of other changes over long periods of time (e.g., road works, introduced traffic calming initiatives, etc.). This is especiall… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04667v1-abstract-full').style.display = 'inline'; document.getElementById('2208.04667v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.04667v1-abstract-full" style="display: none;"> Predicting travel time under rare temporal conditions (e.g., public holidays, school vacation period, etc.) constitutes a challenge due to the limitation of historical data. If at all available, historical data often form a heterogeneous time series due to high probability of other changes over long periods of time (e.g., road works, introduced traffic calming initiatives, etc.). This is especially prominent in cities and suburban areas. We present a vector-space model for encoding rare temporal conditions, that allows coherent representation learning across different temporal conditions. We show increased performance for travel time prediction over different baselines when utilizing the vector-space encoding for representing the temporal setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04667v1-abstract-full').style.display = 'none'; document.getElementById('2208.04667v1-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.04040">arXiv:2208.04040</a> <span> [<a href="https://arxiv.org/pdf/2208.04040">pdf</a>, <a href="https://arxiv.org/format/2208.04040">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"> Eight Years of Face Recognition Research: Reproducibility, Achievements and Open Issues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pereira%2C+T+d+F">Tiago de Freitas Pereira</a>, <a href="/search/cs?searchtype=author&query=Schmidli%2C+D">Dominic Schmidli</a>, <a href="/search/cs?searchtype=author&query=Linghu%2C+Y">Yu Linghu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+X">Xinyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Marcel%2C+S">S茅bastien Marcel</a>, <a href="/search/cs?searchtype=author&query=G%C3%BCnther%2C+M">Manuel G眉nther</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="2208.04040v2-abstract-short" style="display: inline;"> Automatic face recognition is a research area with high popularity. Many different face recognition algorithms have been proposed in the last thirty years of intensive research in the field. With the popularity of deep learning and its capability to solve a huge variety of different problems, face recognition researchers have concentrated effort on creating better models under this paradigm. From… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04040v2-abstract-full').style.display = 'inline'; document.getElementById('2208.04040v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.04040v2-abstract-full" style="display: none;"> Automatic face recognition is a research area with high popularity. Many different face recognition algorithms have been proposed in the last thirty years of intensive research in the field. With the popularity of deep learning and its capability to solve a huge variety of different problems, face recognition researchers have concentrated effort on creating better models under this paradigm. From the year 2015, state-of-the-art face recognition has been rooted in deep learning models. Despite the availability of large-scale and diverse datasets for evaluating the performance of face recognition algorithms, many of the modern datasets just combine different factors that influence face recognition, such as face pose, occlusion, illumination, facial expression and image quality. When algorithms produce errors on these datasets, it is not clear which of the factors has caused this error and, hence, there is no guidance in which direction more research is required. This work is a followup from our previous works developed in 2014 and eventually published in 2016, showing the impact of various facial aspects on face recognition algorithms. By comparing the current state-of-the-art with the best systems from the past, we demonstrate that faces under strong occlusions, some types of illumination, and strong expressions are problems mastered by deep learning algorithms, whereas recognition with low-resolution images, extreme pose variations, and open-set recognition is still an open problem. To show this, we run a sequence of experiments using six different datasets and five different face recognition algorithms in an open-source and reproducible manner. We provide the source code to run all of our experiments, which is easily extensible so that utilizing your own deep network in our evaluation is just a few minutes away. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.04040v2-abstract-full').style.display = 'none'; document.getElementById('2208.04040v2-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.02716">arXiv:2208.02716</a> <span> [<a href="https://arxiv.org/pdf/2208.02716">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> IT/IST/IPLeiria Response to the Call for Proposals on JPEG Pleno Point Cloud Coding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guarda%2C+A+F+R">Andr茅 F. R. Guarda</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+N+M+M">Nuno M. M. Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Ruivo%2C+M">Manuel Ruivo</a>, <a href="/search/cs?searchtype=author&query=Coelho%2C+L">Lu铆s Coelho</a>, <a href="/search/cs?searchtype=author&query=Seleem%2C+A">Abdelrahman Seleem</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Fernando Pereira</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="2208.02716v1-abstract-short" style="display: inline;"> This document describes a deep learning-based point cloud geometry codec and a deep learning-based point cloud joint geometry and colour codec, submitted to the Call for Proposals on JPEG Pleno Point Cloud Coding issued in January 2022. The proposed codecs are based on recent developments in deep learning-based PC geometry coding and offer some of the key functionalities targeted by the Call for P… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.02716v1-abstract-full').style.display = 'inline'; document.getElementById('2208.02716v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.02716v1-abstract-full" style="display: none;"> This document describes a deep learning-based point cloud geometry codec and a deep learning-based point cloud joint geometry and colour codec, submitted to the Call for Proposals on JPEG Pleno Point Cloud Coding issued in January 2022. The proposed codecs are based on recent developments in deep learning-based PC geometry coding and offer some of the key functionalities targeted by the Call for Proposals. The proposed geometry codec offers a compression efficiency that outperforms the MPEG G-PCC standard and outperforms or is competitive with the V-PCC Intra standard for the JPEG Call for Proposals test set; however, the same does not happen for the joint geometry and colour codec due to a quality saturation effect that needs to be overcome. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.02716v1-abstract-full').style.display = 'none'; document.getElementById('2208.02716v1-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 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">52 pages, 8 figures. Document submitted to the 96th ISO/IEC JTC 1/SC 29/WG 1 (JPEG) meeting</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.10186">arXiv:2205.10186</a> <span> [<a href="https://arxiv.org/pdf/2205.10186">pdf</a>, <a href="https://arxiv.org/format/2205.10186">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"> Bayesian Active Learning with Fully Bayesian Gaussian Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Riis%2C+C">Christoffer Riis</a>, <a href="/search/cs?searchtype=author&query=Antunes%2C+F">Francisco Antunes</a>, <a href="/search/cs?searchtype=author&query=H%C3%BCttel%2C+F+B">Frederik Boe H眉ttel</a>, <a href="/search/cs?searchtype=author&query=Azevedo%2C+C+L">Carlos Lima Azevedo</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C芒mara Pereira</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="2205.10186v3-abstract-short" style="display: inline;"> The bias-variance trade-off is a well-known problem in machine learning that only gets more pronounced the less available data there is. In active learning, where labeled data is scarce or difficult to obtain, neglecting this trade-off can cause inefficient and non-optimal querying, leading to unnecessary data labeling. In this paper, we focus on active learning with Gaussian Processes (GPs). For… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10186v3-abstract-full').style.display = 'inline'; document.getElementById('2205.10186v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.10186v3-abstract-full" style="display: none;"> The bias-variance trade-off is a well-known problem in machine learning that only gets more pronounced the less available data there is. In active learning, where labeled data is scarce or difficult to obtain, neglecting this trade-off can cause inefficient and non-optimal querying, leading to unnecessary data labeling. In this paper, we focus on active learning with Gaussian Processes (GPs). For the GP, the bias-variance trade-off is made by optimization of the two hyperparameters: the length scale and noise-term. Considering that the optimal mode of the joint posterior of the hyperparameters is equivalent to the optimal bias-variance trade-off, we approximate this joint posterior and utilize it to design two new acquisition functions. The first one is a Bayesian variant of Query-by-Committee (B-QBC), and the second is an extension that explicitly minimizes the predictive variance through a Query by Mixture of Gaussian Processes (QB-MGP) formulation. Across six simulators, we empirically show that B-QBC, on average, achieves the best marginal likelihood, whereas QB-MGP achieves the best predictive performance. We show that incorporating the bias-variance trade-off in the acquisition functions mitigates unnecessary and expensive data labeling. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.10186v3-abstract-full').style.display = 'none'; document.getElementById('2205.10186v3-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 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 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">In Proceedings of Advances in Neural Information Processing Systems 35 (NeurIPS 2022)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.05032">arXiv:2205.05032</a> <span> [<a href="https://arxiv.org/pdf/2205.05032">pdf</a>, <a href="https://arxiv.org/format/2205.05032">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="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Populations and Evolution">q-bio.PE</span> </div> </div> <p class="title is-5 mathjax"> Brazilian COVID-19 data streaming </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=da+Silva%2C+N+B">N铆vea B. da Silva</a>, <a href="/search/cs?searchtype=author&query=Valencia%2C+L+I+O">Luis Iv谩n O. Valencia</a>, <a href="/search/cs?searchtype=author&query=Filho%2C+F+M+H+S">F谩bio M. H. S. Filho</a>, <a href="/search/cs?searchtype=author&query=Ferreira%2C+A+C+S">Andressa C. S. Ferreira</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+A+C">Felipe A. C. Pereira</a>, <a href="/search/cs?searchtype=author&query=de+Oliveira%2C+G+L">Guilherme L. de Oliveira</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+P+F">Paloma F. Oliveira</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+M+S">Moreno S. Rodrigues</a>, <a href="/search/cs?searchtype=author&query=Ramos%2C+P+I+P">Pablo I. P. Ramos</a>, <a href="/search/cs?searchtype=author&query=Oliveira%2C+J+F">Juliane F. Oliveira</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="2205.05032v1-abstract-short" style="display: inline;"> We collected individualized (unidentifiable) and aggregated openly available data from various sources related to suspected/confirmed SARS-CoV-2 infections, vaccinations, non-pharmaceutical government interventions, human mobility, and levels of population inequality in Brazil. In addition, a data structure allowing real-time data collection, curation, integration, and extract-transform-load proce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.05032v1-abstract-full').style.display = 'inline'; document.getElementById('2205.05032v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.05032v1-abstract-full" style="display: none;"> We collected individualized (unidentifiable) and aggregated openly available data from various sources related to suspected/confirmed SARS-CoV-2 infections, vaccinations, non-pharmaceutical government interventions, human mobility, and levels of population inequality in Brazil. In addition, a data structure allowing real-time data collection, curation, integration, and extract-transform-load processes for different objectives was developed. The granularity of this dataset (state- and municipality-wide) enables its application to individualized and ecological epidemiological studies, statistical, mathematical, and computational modeling, data visualization as well as the scientific dissemination of information on the COVID-19 pandemic in Brazil. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.05032v1-abstract-full').style.display = 'none'; document.getElementById('2205.05032v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 6 figures, 2 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/2205.01317">arXiv:2205.01317</a> <span> [<a href="https://arxiv.org/pdf/2205.01317">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="General Economics">econ.GN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</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.trc.2022.103589">10.1016/j.trc.2022.103589 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Open vs Closed-ended questions in attitudinal surveys -- comparing, combining, and interpreting using natural language processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Baburajan%2C+V">Vishnu Baburajan</a>, <a href="/search/cs?searchtype=author&query=Silva%2C+J+d+A+e">Jo茫o de Abreu e Silva</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco Camara Pereira</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="2205.01317v1-abstract-short" style="display: inline;"> To improve the traveling experience, researchers have been analyzing the role of attitudes in travel behavior modeling. Although most researchers use closed-ended surveys, the appropriate method to measure attitudes is debatable. Topic Modeling could significantly reduce the time to extract information from open-ended responses and eliminate subjective bias, thereby alleviating analyst concerns. O… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.01317v1-abstract-full').style.display = 'inline'; document.getElementById('2205.01317v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.01317v1-abstract-full" style="display: none;"> To improve the traveling experience, researchers have been analyzing the role of attitudes in travel behavior modeling. Although most researchers use closed-ended surveys, the appropriate method to measure attitudes is debatable. Topic Modeling could significantly reduce the time to extract information from open-ended responses and eliminate subjective bias, thereby alleviating analyst concerns. Our research uses Topic Modeling to extract information from open-ended questions and compare its performance with closed-ended responses. Furthermore, some respondents might prefer answering questions using their preferred questionnaire type. So, we propose a modeling framework that allows respondents to use their preferred questionnaire type to answer the survey and enable analysts to use the modeling frameworks of their choice to predict behavior. We demonstrate this using a dataset collected from the USA that measures the intention to use Autonomous Vehicles for commute trips. Respondents were presented with alternative questionnaire versions (open- and closed- ended). Since our objective was also to compare the performance of alternative questionnaire versions, the survey was designed to eliminate influences resulting from statements, behavioral framework, and the choice experiment. Results indicate the suitability of using Topic Modeling to extract information from open-ended responses; however, the models estimated using the closed-ended questions perform better compared to them. Besides, the proposed model performs better compared to the models used currently. Furthermore, our proposed framework will allow respondents to choose the questionnaire type to answer, which could be particularly beneficial to them when using voice-based surveys. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.01317v1-abstract-full').style.display = 'none'; document.getElementById('2205.01317v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.00756">arXiv:2205.00756</a> <span> [<a href="https://arxiv.org/pdf/2205.00756">pdf</a>, <a href="https://arxiv.org/format/2205.00756">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="Applications">stat.AP</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"> VICE: Variational Interpretable Concept Embeddings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Muttenthaler%2C+L">Lukas Muttenthaler</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+C+Y">Charles Y. Zheng</a>, <a href="/search/cs?searchtype=author&query=McClure%2C+P">Patrick McClure</a>, <a href="/search/cs?searchtype=author&query=Vandermeulen%2C+R+A">Robert A. Vandermeulen</a>, <a href="/search/cs?searchtype=author&query=Hebart%2C+M+N">Martin N. Hebart</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Francisco Pereira</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="2205.00756v8-abstract-short" style="display: inline;"> A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.00756v8-abstract-full').style.display = 'inline'; document.getElementById('2205.00756v8-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.00756v8-abstract-full" style="display: none;"> A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.00756v8-abstract-full').style.display = 'none'; document.getElementById('2205.00756v8-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 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">Accepted at NeurIPS 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.04322">arXiv:2204.04322</a> <span> [<a href="https://arxiv.org/pdf/2204.04322">pdf</a>, <a href="https://arxiv.org/format/2204.04322">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"> Iterative Depth-First Search for Fully Observable Non-Deterministic Planning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pereira%2C+R+F">Ramon Fraga Pereira</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+A+G">Andr茅 G. Pereira</a>, <a href="/search/cs?searchtype=author&query=Messa%2C+F">Frederico Messa</a>, <a href="/search/cs?searchtype=author&query=De+Giacomo%2C+G">Giuseppe De Giacomo</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="2204.04322v3-abstract-short" style="display: inline;"> Fully Observable Non-Deterministic (FOND) planning models uncertainty through actions with non-deterministic effects. Existing FOND planning algorithms are effective and employ a wide range of techniques. However, most of the existing algorithms are not robust for dealing with both non-determinism and task size. In this paper, we develop a novel iterative depth-first search algorithm that solves F… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.04322v3-abstract-full').style.display = 'inline'; document.getElementById('2204.04322v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.04322v3-abstract-full" style="display: none;"> Fully Observable Non-Deterministic (FOND) planning models uncertainty through actions with non-deterministic effects. Existing FOND planning algorithms are effective and employ a wide range of techniques. However, most of the existing algorithms are not robust for dealing with both non-determinism and task size. In this paper, we develop a novel iterative depth-first search algorithm that solves FOND planning tasks and produces strong cyclic policies. Our algorithm is explicitly designed for FOND planning, addressing more directly the non-deterministic aspect of FOND planning, and it also exploits the benefits of heuristic functions to make the algorithm more effective during the iterative searching process. We compare our proposed algorithm to well-known FOND planners, and show that it has robust performance over several distinct types of FOND domains considering different metrics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.04322v3-abstract-full').style.display = 'none'; document.getElementById('2204.04322v3-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.09279">arXiv:2203.09279</a> <span> [<a href="https://arxiv.org/pdf/2203.09279">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Transfer learning for cross-modal demand prediction of bike-share and public transit </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hua%2C+M">Mingzhuang Hua</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco Camara Pereira</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yu Jiang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuewu 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="2203.09279v1-abstract-short" style="display: inline;"> The urban transportation system is a combination of multiple transport modes, and the interdependencies across those modes exist. This means that the travel demand across different travel modes could be correlated as one mode may receive demand from or create demand for another mode, not to mention natural correlations between different demand time series due to general demand flow patterns across… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.09279v1-abstract-full').style.display = 'inline'; document.getElementById('2203.09279v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.09279v1-abstract-full" style="display: none;"> The urban transportation system is a combination of multiple transport modes, and the interdependencies across those modes exist. This means that the travel demand across different travel modes could be correlated as one mode may receive demand from or create demand for another mode, not to mention natural correlations between different demand time series due to general demand flow patterns across the network. It is expectable that cross-modal ripple effects become more prevalent, with Mobility as a Service. Therefore, by propagating demand data across modes, a better demand prediction could be obtained. To this end, this study explores various machine learning models and transfer learning strategies for cross-modal demand prediction. The trip data of bike-share, metro, and taxi are processed as the station-level passenger flows, and then the proposed prediction method is tested in the large-scale case studies of Nanjing and Chicago. The results suggest that prediction models with transfer learning perform better than unimodal prediction models. Furthermore, stacked Long Short-Term Memory model performs particularly well in cross-modal demand prediction. These results verify our combined method's forecasting improvement over existing benchmarks and demonstrate the good transferability for cross-modal demand prediction in multiple cities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.09279v1-abstract-full').style.display = 'none'; document.getElementById('2203.09279v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">27 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.11962">arXiv:2202.11962</a> <span> [<a href="https://arxiv.org/pdf/2202.11962">pdf</a>, <a href="https://arxiv.org/format/2202.11962">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Large Scale Passenger Detection with Smartphone/Bus Implicit Interaction and Multisensory Unsupervised Cause-effect Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Servizi%2C+V">Valentino Servizi</a>, <a href="/search/cs?searchtype=author&query=Persson%2C+D+R">Dan R. Persson</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C. Pereira</a>, <a href="/search/cs?searchtype=author&query=Villadsen%2C+H">Hannah Villadsen</a>, <a href="/search/cs?searchtype=author&query=B%C3%A6kgaard%2C+P">Per B忙kgaard</a>, <a href="/search/cs?searchtype=author&query=Rich%2C+J">Jeppe Rich</a>, <a href="/search/cs?searchtype=author&query=Nielsen%2C+O+A">Otto A. Nielsen</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="2202.11962v1-abstract-short" style="display: inline;"> Intelligent Transportation Systems (ITS) underpin the concept of Mobility as a Service (MaaS), which requires universal and seamless users' access across multiple public and private transportation systems while allowing operators' proportional revenue sharing. Current user sensing technologies such as Walk-in/Walk-out (WIWO) and Check-in/Check-out (CICO) have limited scalability for large-scale de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11962v1-abstract-full').style.display = 'inline'; document.getElementById('2202.11962v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.11962v1-abstract-full" style="display: none;"> Intelligent Transportation Systems (ITS) underpin the concept of Mobility as a Service (MaaS), which requires universal and seamless users' access across multiple public and private transportation systems while allowing operators' proportional revenue sharing. Current user sensing technologies such as Walk-in/Walk-out (WIWO) and Check-in/Check-out (CICO) have limited scalability for large-scale deployments. These limitations prevent ITS from supporting analysis, optimization, calculation of revenue sharing, and control of MaaS comfort, safety, and efficiency. We focus on the concept of implicit Be-in/Be-out (BIBO) smartphone-sensing and classification. To close the gap and enhance smartphones towards MaaS, we developed a proprietary smartphone-sensing platform collecting contemporary Bluetooth Low Energy (BLE) signals from BLE devices installed on buses and Global Positioning System (GPS) locations of both buses and smartphones. To enable the training of a model based on GPS features against the BLE pseudo-label, we propose the Cause-Effect Multitask Wasserstein Autoencoder (CEMWA). CEMWA combines and extends several frameworks around Wasserstein autoencoders and neural networks. As a dimensionality reduction tool, CEMWA obtains an auto-validated representation of a latent space describing users' smartphones within the transport system. This representation allows BIBO clustering via DBSCAN. We perform an ablation study of CEMWA's alternative architectures and benchmark against the best available supervised methods. We analyze performance's sensitivity to label quality. Under the na茂ve assumption of accurate ground truth, XGBoost outperforms CEMWA. Although XGBoost and Random Forest prove to be tolerant to label noise, CEMWA is agnostic to label noise by design and provides the best performance with an 88\% F1 score. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11962v1-abstract-full').style.display = 'none'; document.getElementById('2202.11962v1-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">20 pages, 13 figures, 3 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/2202.11961">arXiv:2202.11961</a> <span> [<a href="https://arxiv.org/pdf/2202.11961">pdf</a>, <a href="https://arxiv.org/format/2202.11961">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 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/TITS.2023.3291493">10.1109/TITS.2023.3291493 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> "Is not the truth the truth?": Analyzing the Impact of User Validations for Bus In/Out Detection in Smartphone-based Surveys </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Servizi.%2C+V">Valentino Servizi.</a>, <a href="/search/cs?searchtype=author&query=Persson%2C+D+R">Dan R. Persson</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C. Pereira</a>, <a href="/search/cs?searchtype=author&query=Villadsen%2C+H">Hannah Villadsen</a>, <a href="/search/cs?searchtype=author&query=B%C3%A6kgaard%2C+P">Per B忙kgaard</a>, <a href="/search/cs?searchtype=author&query=Peled%2C+I">Inon Peled</a>, <a href="/search/cs?searchtype=author&query=Nielsen%2C+O+A">Otto A. Nielsen</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="2202.11961v1-abstract-short" style="display: inline;"> Passenger flow allows the study of users' behavior through the public network and assists in designing new facilities and services. This flow is observed through interactions between passengers and infrastructure. For this task, Bluetooth technology and smartphones represent the ideal solution. The latter component allows users' identification, authentication, and billing, while the former allows… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11961v1-abstract-full').style.display = 'inline'; document.getElementById('2202.11961v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.11961v1-abstract-full" style="display: none;"> Passenger flow allows the study of users' behavior through the public network and assists in designing new facilities and services. This flow is observed through interactions between passengers and infrastructure. For this task, Bluetooth technology and smartphones represent the ideal solution. The latter component allows users' identification, authentication, and billing, while the former allows short-range implicit interactions, device-to-device. To assess the potential of such a use case, we need to verify how robust Bluetooth signal and related machine learning (ML) classifiers are against the noise of realistic contexts. Therefore, we model binary passenger states with respect to a public vehicle, where one can either be-in or be-out (BIBO). The BIBO label identifies a fundamental building block of continuously-valued passenger flow. This paper describes the Human-Computer interaction experimental setting in a semi-controlled environment, which involves: two autonomous vehicles operating on two routes, serving three bus stops and eighteen users, as well as a proprietary smartphone-Bluetooth sensing platform. The resulting dataset includes multiple sensors' measurements of the same event and two ground-truth levels, the first being validation by participants, the second by three video-cameras surveilling buses and track. We performed a Monte-Carlo simulation of labels-flip to emulate human errors in the labeling process, as is known to happen in smartphone surveys; next we used such flipped labels for supervised training of ML classifiers. The impact of errors on model performance bias can be large. Results show ML tolerance to label flips caused by human or machine errors up to 30%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11961v1-abstract-full').style.display = 'none'; document.getElementById('2202.11961v1-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">22 pages, 11 figures, 4 tables, 3 algorithms</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.10307">arXiv:2201.10307</a> <span> [<a href="https://arxiv.org/pdf/2201.10307">pdf</a>, <a href="https://arxiv.org/format/2201.10307">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"> Unboxing the graph: Neural Relational Inference for Mobility Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tygesen%2C+M+N">Mathias Niemann Tygesen</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C. Pereira</a>, <a href="/search/cs?searchtype=author&query=Rodrigues%2C+F">Filipe Rodrigues</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="2201.10307v1-abstract-short" style="display: inline;"> Predicting the supply and demand of transport systems is vital for efficient traffic management, control, optimization, and planning. For example, predicting where from/to and when people intend to travel by taxi can support fleet managers to distribute resources; better predicting traffic speeds/congestion allows for pro-active control measures or for users to better choose their paths. Making sp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.10307v1-abstract-full').style.display = 'inline'; document.getElementById('2201.10307v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.10307v1-abstract-full" style="display: none;"> Predicting the supply and demand of transport systems is vital for efficient traffic management, control, optimization, and planning. For example, predicting where from/to and when people intend to travel by taxi can support fleet managers to distribute resources; better predicting traffic speeds/congestion allows for pro-active control measures or for users to better choose their paths. Making spatio-temporal predictions is known to be a hard task, but recently Graph Neural Networks (GNNs) have been widely applied on non-euclidean spatial data. However, most GNN models require a predefined graph, and so far, researchers rely on heuristics to generate this graph for the model to use. In this paper, we use Neural Relational Inference to learn the optimal graph for the model. Our approach has several advantages: 1) a Variational Auto Encoder structure allows for the graph to be dynamically determined by the data, potentially changing through time; 2) the encoder structure allows the use of external data in the generation of the graph; 3) it is possible to place Bayesian priors on the generated graphs to encode domain knowledge. We conduct experiments on two datasets, namely the NYC Yellow Taxi and the PEMS road traffic datasets. In both datasets, we outperform benchmarks and show performance comparable to state-of-the-art. Furthermore, we do an in-depth analysis of the learned graphs, providing insights on what kinds of connections GNNs use for spatio-temporal predictions in the transport domain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.10307v1-abstract-full').style.display = 'none'; document.getElementById('2201.10307v1-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> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.11135">arXiv:2111.11135</a> <span> [<a href="https://arxiv.org/pdf/2111.11135">pdf</a>, <a href="https://arxiv.org/ps/2111.11135">ps</a>, <a href="https://arxiv.org/format/2111.11135">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey 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/10.3390/e24010005">10.3390/e24010005 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Error Probability Mitigation in Quantum Reading using Classical Codes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pereira%2C+F+R+F">Francisco Revson Fernandes Pereira</a>, <a href="/search/cs?searchtype=author&query=Mancini%2C+S">Stefano Mancini</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="2111.11135v1-abstract-short" style="display: inline;"> A general framework describing the statistical discrimination of an ensemble of quantum channels is given by the name of quantum reading. Several tools can be applied in quantum reading to reduce the error probability in distinguishing the ensemble of channels. Classical and quantum codes can be envisioned for this goal. The aim of this paper is to present a simple but fruitful protocol for this t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.11135v1-abstract-full').style.display = 'inline'; document.getElementById('2111.11135v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.11135v1-abstract-full" style="display: none;"> A general framework describing the statistical discrimination of an ensemble of quantum channels is given by the name of quantum reading. Several tools can be applied in quantum reading to reduce the error probability in distinguishing the ensemble of channels. Classical and quantum codes can be envisioned for this goal. The aim of this paper is to present a simple but fruitful protocol for this task using classical error-correcting codes. Three families of codes are considered: Reed-Solomon codes, BCH codes, and Reed-Muller codes. In conjunction to the use of codes, we also analyze the role of the receiver. In particular, heterodyne and Dolinar receivers are taken in consideration. The encoding and measurement schemes are connected by the probing step. As probe we consider coherent states. In such simple manner, interesting results are obtained. As we show, for any fixed rate and code, there is a threshold under which using codes surpass optimal and sophisticated schemes. However, there are codes and receiver schemes giving lower thresholds. BCH codes in conjunction with Dolinar receiver turn out to be the optimal strategy for error mitigation in the quantum reading task. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.11135v1-abstract-full').style.display = 'none'; document.getElementById('2111.11135v1-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">Journal ref:</span> Entropy 2022, 24(1), 5 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.12042">arXiv:2109.12042</a> <span> [<a href="https://arxiv.org/pdf/2109.12042">pdf</a>, <a href="https://arxiv.org/format/2109.12042">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">stat.ML</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="Econometrics">econ.EM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Arkoudi%2C+I">Ioanna Arkoudi</a>, <a href="/search/cs?searchtype=author&query=Azevedo%2C+C+L">Carlos Lima Azevedo</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F+C">Francisco C. Pereira</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2109.12042v2-abstract-short" style="display: inline;"> This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs). In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables with a special focus on interpretability and model transparency. Although embedding representations within the logit framework have been… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.12042v2-abstract-full').style.display = 'inline'; document.getElementById('2109.12042v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.12042v2-abstract-full" style="display: none;"> This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs). In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables with a special focus on interpretability and model transparency. Although embedding representations within the logit framework have been conceptualized by Pereira (2019), their dimensions do not have an absolute definitive meaning, hence offering limited behavioral insights in this earlier work. The novelty of our work lies in enforcing interpretability to the embedding vectors by formally associating each of their dimensions to a choice alternative. Thus, our approach brings benefits much beyond a simple parsimonious representation improvement over dummy encoding, as it provides behaviorally meaningful outputs that can be used in travel demand analysis and policy decisions. Additionally, in contrast to previously suggested ANN-based Discrete Choice Models (DCMs) that either sacrifice interpretability for performance or are only partially interpretable, our models preserve interpretability of the utility coefficients for all the input variables despite being based on ANN principles. The proposed models were tested on two real world datasets and evaluated against benchmark and baseline models that use dummy-encoding. The results of the experiments indicate that our models deliver state-of-the-art predictive performance, outperforming existing ANN-based models while drastically reducing the number of required network parameters. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.12042v2-abstract-full').style.display = 'none'; document.getElementById('2109.12042v2-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.02481">arXiv:2108.02481</a> <span> [<a href="https://arxiv.org/pdf/2108.02481">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> Joint Geometry and Color Projection-based Point Cloud Quality Metric </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Javaheri%2C+A">Alireza Javaheri</a>, <a href="/search/cs?searchtype=author&query=Brites%2C+C">Catarina Brites</a>, <a href="/search/cs?searchtype=author&query=Pereira%2C+F">Fernando Pereira</a>, <a href="/search/cs?searchtype=author&query=Ascenso%2C+J">Jo茫o Ascenso</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="2108.02481v1-abstract-short" style="display: inline;"> Point cloud coding solutions have been recently standardized to address the needs of multiple application scenarios. The design and assessment of point cloud coding methods require reliable objective quality metrics to evaluate the level of degradation introduced by compression or any other type of processing. Several point cloud objective quality metrics has been recently proposed to reliable est… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.02481v1-abstract-full').style.display = 'inline'; document.getElementById('2108.02481v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.02481v1-abstract-full" style="display: none;"> Point cloud coding solutions have been recently standardized to address the needs of multiple application scenarios. The design and assessment of point cloud coding methods require reliable objective quality metrics to evaluate the level of degradation introduced by compression or any other type of processing. Several point cloud objective quality metrics has been recently proposed to reliable estimate human perceived quality, including the so-called projection-based metrics. In this context, this paper proposes a joint geometry and color projection-based point cloud objective quality metric which solves the critical weakness of this type of quality metrics, i.e., the misalignment between the reference and degraded projected images. Moreover, the proposed point cloud quality metric exploits the best performing 2D quality metrics in the literature to assess the quality of the projected images. The experimental results show that the proposed projection-based quality metric offers the best subjective-objective correlation performance in comparison with other metrics in the literature. The Pearson correlation gains regarding D1-PSNR and D2-PSNR metrics are 17% and 14.2 when data with all coding degradations is considered. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.02481v1-abstract-full').style.display = 'none'; document.getElementById('2108.02481v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">This article has been submitted to IEEE Transactions on Multimedia</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=Pereira%2C+F&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Pereira%2C+F&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Pereira%2C+F&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Pereira%2C+F&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </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