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 51 results for author: <span class="mathjax">Davies, M E</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=Davies%2C+M+E">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="Davies, M E"> </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=Davies%2C+M+E&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="Davies, M E"> <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=Davies%2C+M+E&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Davies%2C+M+E&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Davies%2C+M+E&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.21303">arXiv:2410.21303</a> <span> [<a href="https://arxiv.org/pdf/2410.21303">pdf</a>, <a href="https://arxiv.org/format/2410.21303">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> VEMOCLAP: A video emotion classification web application </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sulun%2C+S">Serkan Sulun</a>, <a href="/search/cs?searchtype=author&query=Viana%2C+P">Paula Viana</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</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="2410.21303v1-abstract-short" style="display: inline;"> We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attent… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21303v1-abstract-full').style.display = 'inline'; document.getElementById('2410.21303v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.21303v1-abstract-full" style="display: none;"> We introduce VEMOCLAP: Video EMOtion Classifier using Pretrained features, the first readily available and open-source web application that analyzes the emotional content of any user-provided video. We improve our previous work, which exploits open-source pretrained models that work on video frames and audio, and then efficiently fuse the resulting pretrained features using multi-head cross-attention. Our approach increases the state-of-the-art classification accuracy on the Ekman-6 video emotion dataset by 4.3% and offers an online application for users to run our model on their own videos or YouTube videos. We invite the readers to try our application at serkansulun.com/app. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.21303v1-abstract-full').style.display = 'none'; document.getElementById('2410.21303v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to 2024 IEEE International Symposium on Multimedia (ISM), Tokyo, Japan</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.19760">arXiv:2410.19760</a> <span> [<a href="https://arxiv.org/pdf/2410.19760">pdf</a>, <a href="https://arxiv.org/format/2410.19760">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> <div 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.eswa.2024.125209">10.1016/j.eswa.2024.125209 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Movie Trailer Genre Classification Using Multimodal Pretrained Features </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sulun%2C+S">Serkan Sulun</a>, <a href="/search/cs?searchtype=author&query=Viana%2C+P">Paula Viana</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</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="2410.19760v1-abstract-short" style="display: inline;"> We introduce a novel method for movie genre classification, capitalizing on a diverse set of readily accessible pretrained models. These models extract high-level features related to visual scenery, objects, characters, text, speech, music, and audio effects. To intelligently fuse these pretrained features, we train small classifier models with low time and memory requirements. Employing the trans… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19760v1-abstract-full').style.display = 'inline'; document.getElementById('2410.19760v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.19760v1-abstract-full" style="display: none;"> We introduce a novel method for movie genre classification, capitalizing on a diverse set of readily accessible pretrained models. These models extract high-level features related to visual scenery, objects, characters, text, speech, music, and audio effects. To intelligently fuse these pretrained features, we train small classifier models with low time and memory requirements. Employing the transformer model, our approach utilizes all video and audio frames of movie trailers without performing any temporal pooling, efficiently exploiting the correspondence between all elements, as opposed to the fixed and low number of frames typically used by traditional methods. Our approach fuses features originating from different tasks and modalities, with different dimensionalities, different temporal lengths, and complex dependencies as opposed to current approaches. Our method outperforms state-of-the-art movie genre classification models in terms of precision, recall, and mean average precision (mAP). To foster future research, we make the pretrained features for the entire MovieNet dataset, along with our genre classification code and the trained models, publicly available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.19760v1-abstract-full').style.display = 'none'; document.getElementById('2410.19760v1-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> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Expert Systems with Applications 258 (2024) 125209 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.08902">arXiv:2401.08902</a> <span> [<a href="https://arxiv.org/pdf/2401.08902">pdf</a>, <a href="https://arxiv.org/format/2401.08902">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Similar but Faster: Manipulation of Tempo in Music Audio Embeddings for Tempo Prediction and Search </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=McCallum%2C+M+C">Matthew C. McCallum</a>, <a href="/search/cs?searchtype=author&query=Henkel%2C+F">Florian Henkel</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Jaehun Kim</a>, <a href="/search/cs?searchtype=author&query=Sandberg%2C+S+E">Samuel E. Sandberg</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</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="2401.08902v1-abstract-short" style="display: inline;"> Audio embeddings enable large scale comparisons of the similarity of audio files for applications such as search and recommendation. Due to the subjectivity of audio similarity, it can be desirable to design systems that answer not only whether audio is similar, but similar in what way (e.g., wrt. tempo, mood or genre). Previous works have proposed disentangled embedding spaces where subspaces rep… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08902v1-abstract-full').style.display = 'inline'; document.getElementById('2401.08902v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.08902v1-abstract-full" style="display: none;"> Audio embeddings enable large scale comparisons of the similarity of audio files for applications such as search and recommendation. Due to the subjectivity of audio similarity, it can be desirable to design systems that answer not only whether audio is similar, but similar in what way (e.g., wrt. tempo, mood or genre). Previous works have proposed disentangled embedding spaces where subspaces representing specific, yet possibly correlated, attributes can be weighted to emphasize those attributes in downstream tasks. However, no research has been conducted into the independence of these subspaces, nor their manipulation, in order to retrieve tracks that are similar but different in a specific way. Here, we explore the manipulation of tempo in embedding spaces as a case-study towards this goal. We propose tempo translation functions that allow for efficient manipulation of tempo within a pre-existing embedding space whilst maintaining other properties such as genre. As this translation is specific to tempo it enables retrieval of tracks that are similar but have specifically different tempi. We show that such a function can be used as an efficient data augmentation strategy for both training of downstream tempo predictors, and improved nearest neighbor retrieval of properties largely independent of tempo. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08902v1-abstract-full').style.display = 'none'; document.getElementById('2401.08902v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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 to the International Conference on Acoustics, Speech and Signal Processing (ICASSP) 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/2401.08891">arXiv:2401.08891</a> <span> [<a href="https://arxiv.org/pdf/2401.08891">pdf</a>, <a href="https://arxiv.org/format/2401.08891">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Tempo estimation as fully self-supervised binary classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Henkel%2C+F">Florian Henkel</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Jaehun Kim</a>, <a href="/search/cs?searchtype=author&query=McCallum%2C+M+C">Matthew C. McCallum</a>, <a href="/search/cs?searchtype=author&query=Sandberg%2C+S+E">Samuel E. Sandberg</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</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="2401.08891v1-abstract-short" style="display: inline;"> This paper addresses the problem of global tempo estimation in musical audio. Given that annotating tempo is time-consuming and requires certain musical expertise, few publicly available data sources exist to train machine learning models for this task. Towards alleviating this issue, we propose a fully self-supervised approach that does not rely on any human labeled data. Our method builds on the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08891v1-abstract-full').style.display = 'inline'; document.getElementById('2401.08891v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.08891v1-abstract-full" style="display: none;"> This paper addresses the problem of global tempo estimation in musical audio. Given that annotating tempo is time-consuming and requires certain musical expertise, few publicly available data sources exist to train machine learning models for this task. Towards alleviating this issue, we propose a fully self-supervised approach that does not rely on any human labeled data. Our method builds on the fact that generic (music) audio embeddings already encode a variety of properties, including information about tempo, making them easily adaptable for downstream tasks. While recent work in self-supervised tempo estimation aimed to learn a tempo specific representation that was subsequently used to train a supervised classifier, we reformulate the task into the binary classification problem of predicting whether a target track has the same or a different tempo compared to a reference. While the former still requires labeled training data for the final classification model, our approach uses arbitrary unlabeled music data in combination with time-stretching for model training as well as a small set of synthetically created reference samples for predicting the final tempo. Evaluation of our approach in comparison with the state-of-the-art reveals highly competitive performance when the constraint of finding the precise tempo octave is relaxed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08891v1-abstract-full').style.display = 'none'; document.getElementById('2401.08891v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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 to the International Conference on Acoustics, Speech and Signal Processing (ICASSP) 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/2401.08889">arXiv:2401.08889</a> <span> [<a href="https://arxiv.org/pdf/2401.08889">pdf</a>, <a href="https://arxiv.org/format/2401.08889">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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="Multimedia">cs.MM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=McCallum%2C+M+C">Matthew C. McCallum</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</a>, <a href="/search/cs?searchtype=author&query=Henkel%2C+F">Florian Henkel</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Jaehun Kim</a>, <a href="/search/cs?searchtype=author&query=Sandberg%2C+S+E">Samuel E. Sandberg</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="2401.08889v1-abstract-short" style="display: inline;"> Audio embeddings are crucial tools in understanding large catalogs of music. Typically embeddings are evaluated on the basis of the performance they provide in a wide range of downstream tasks, however few studies have investigated the local properties of the embedding spaces themselves which are important in nearest neighbor algorithms, commonly used in music search and recommendation. In this wo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08889v1-abstract-full').style.display = 'inline'; document.getElementById('2401.08889v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.08889v1-abstract-full" style="display: none;"> Audio embeddings are crucial tools in understanding large catalogs of music. Typically embeddings are evaluated on the basis of the performance they provide in a wide range of downstream tasks, however few studies have investigated the local properties of the embedding spaces themselves which are important in nearest neighbor algorithms, commonly used in music search and recommendation. In this work we show that when learning audio representations on music datasets via contrastive learning, musical properties that are typically homogeneous within a track (e.g., key and tempo) are reflected in the locality of neighborhoods in the resulting embedding space. By applying appropriate data augmentation strategies, localisation of such properties can not only be reduced but the localisation of other attributes is increased. For example, locality of features such as pitch and tempo that are less relevant to non-expert listeners, may be mitigated while improving the locality of more salient features such as genre and mood, achieving state-of-the-art performance in nearest neighbor retrieval accuracy. Similarly, we show that the optimal selection of data augmentation strategies for contrastive learning of music audio embeddings is dependent on the downstream task, highlighting this as an important embedding design decision. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08889v1-abstract-full').style.display = 'none'; document.getElementById('2401.08889v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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 to the International Conference on Acoustics, Speech and Signal Processing (ICASSP) 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/2308.10355">arXiv:2308.10355</a> <span> [<a href="https://arxiv.org/pdf/2308.10355">pdf</a>, <a href="https://arxiv.org/format/2308.10355">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chiu%2C+C">Ching-Yu Chiu</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+M">Meinard M眉ller</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</a>, <a href="/search/cs?searchtype=author&query=Su%2C+A+W">Alvin Wen-Yu Su</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yi-Hsuan Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.10355v1-abstract-short" style="display: inline;"> To model the periodicity of beats, state-of-the-art beat tracking systems use "post-processing trackers" (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Sc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.10355v1-abstract-full').style.display = 'inline'; document.getElementById('2308.10355v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.10355v1-abstract-full" style="display: none;"> To model the periodicity of beats, state-of-the-art beat tracking systems use "post-processing trackers" (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called "predominant local pulses" (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.10355v1-abstract-full').style.display = 'none'; document.getElementById('2308.10355v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (July 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.06868">arXiv:2304.06868</a> <span> [<a href="https://arxiv.org/pdf/2304.06868">pdf</a>, <a href="https://arxiv.org/format/2304.06868">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> <div 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/ICASSP49357.2023.10095292">10.1109/ICASSP49357.2023.10095292 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Tempo vs. Pitch: understanding self-supervised tempo estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Morais%2C+G">Giovana Morais</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</a>, <a href="/search/cs?searchtype=author&query=Queiroz%2C+M">Marcelo Queiroz</a>, <a href="/search/cs?searchtype=author&query=Fuentes%2C+M">Magdalena Fuentes</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2304.06868v1-abstract-short" style="display: inline;"> Self-supervision methods learn representations by solving pretext tasks that do not require human-generated labels, alleviating the need for time-consuming annotations. These methods have been applied in computer vision, natural language processing, environmental sound analysis, and recently in music information retrieval, e.g. for pitch estimation. Particularly in the context of music, there are… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.06868v1-abstract-full').style.display = 'inline'; document.getElementById('2304.06868v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.06868v1-abstract-full" style="display: none;"> Self-supervision methods learn representations by solving pretext tasks that do not require human-generated labels, alleviating the need for time-consuming annotations. These methods have been applied in computer vision, natural language processing, environmental sound analysis, and recently in music information retrieval, e.g. for pitch estimation. Particularly in the context of music, there are few insights about the fragility of these models regarding different distributions of data, and how they could be mitigated. In this paper, we explore these questions by dissecting a self-supervised model for pitch estimation adapted for tempo estimation via rigorous experimentation with synthetic data. Specifically, we study the relationship between the input representation and data distribution for self-supervised tempo estimation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.06868v1-abstract-full').style.display = 'none'; document.getElementById('2304.06868v1-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 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">5 pages, 3 figures, published on 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.14162">arXiv:2211.14162</a> <span> [<a href="https://arxiv.org/pdf/2211.14162">pdf</a>, <a href="https://arxiv.org/format/2211.14162">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> A Gaussian Process Regression based Dynamical Models Learning Algorithm for Target Tracking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sun%2C+M">Mengwei Sun</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Proudler%2C+I+K">Ian K. Proudler</a>, <a href="/search/cs?searchtype=author&query=Hopgood%2C+J+R">James R. Hopgood</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="2211.14162v1-abstract-short" style="display: inline;"> Maneuvering target tracking is a challenging problem for sensor systems because of the unpredictability of the targets' motions. This paper proposes a novel data-driven method for learning the dynamical motion model of a target. Non-parametric Gaussian process regression (GPR) is used to learn a target's naturally shift invariant motion (NSIM) behavior, which is translationally invariant and does… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.14162v1-abstract-full').style.display = 'inline'; document.getElementById('2211.14162v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.14162v1-abstract-full" style="display: none;"> Maneuvering target tracking is a challenging problem for sensor systems because of the unpredictability of the targets' motions. This paper proposes a novel data-driven method for learning the dynamical motion model of a target. Non-parametric Gaussian process regression (GPR) is used to learn a target's naturally shift invariant motion (NSIM) behavior, which is translationally invariant and does not need to be constantly updated as the target moves. The learned Gaussian processes (GPs) can be applied to track targets within different surveillance regions from the surveillance region of the training data by being incorporated into the particle filter (PF) implementation. The performance of our proposed approach is evaluated over different maneuvering scenarios by being compared with commonly used interacting multiple model (IMM)-PF methods and provides around $90\%$ performance improvement for a multi-target tracking (MTT) highly maneuvering scenario. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.14162v1-abstract-full').style.display = 'none'; document.getElementById('2211.14162v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 November, 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">11 pages, 10 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/2210.06817">arXiv:2210.06817</a> <span> [<a href="https://arxiv.org/pdf/2210.06817">pdf</a>, <a href="https://arxiv.org/format/2210.06817">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</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/LSP.2022.3215106">10.1109/LSP.2022.3215106 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An Analysis Method for Metric-Level Switching in Beat Tracking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chiu%2C+C">Ching-Yu Chiu</a>, <a href="/search/cs?searchtype=author&query=M%C3%BCller%2C+M">Meinard M眉ller</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</a>, <a href="/search/cs?searchtype=author&query=Su%2C+A+W">Alvin Wen-Yu Su</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Y">Yi-Hsuan Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2210.06817v1-abstract-short" style="display: inline;"> For expressive music, the tempo may change over time, posing challenges to tracking the beats by an automatic model. The model may first tap to the correct tempo, but then may fail to adapt to a tempo change, or switch between several incorrect but perceptually plausible ones (e.g., half- or double-tempo). Existing evaluation metrics for beat tracking do not reflect such behaviors, as they typical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06817v1-abstract-full').style.display = 'inline'; document.getElementById('2210.06817v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.06817v1-abstract-full" style="display: none;"> For expressive music, the tempo may change over time, posing challenges to tracking the beats by an automatic model. The model may first tap to the correct tempo, but then may fail to adapt to a tempo change, or switch between several incorrect but perceptually plausible ones (e.g., half- or double-tempo). Existing evaluation metrics for beat tracking do not reflect such behaviors, as they typically assume a fixed relationship between the reference beats and estimated beats. In this paper, we propose a new performance analysis method, called annotation coverage ratio (ACR), that accounts for a variety of possible metric-level switching behaviors of beat trackers. The idea is to derive sequences of modified reference beats of all metrical levels for every two consecutive reference beats, and compare every sequence of modified reference beats to the subsequences of estimated beats. We show via experiments on three datasets of different genres the usefulness of ACR when utilized alongside existing metrics, and discuss the new insights to be gained. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.06817v1-abstract-full').style.display = 'none'; document.getElementById('2210.06817v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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 to IEEE Signal Processing Letters (Oct. 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/2206.10776">arXiv:2206.10776</a> <span> [<a href="https://arxiv.org/pdf/2206.10776">pdf</a>, <a href="https://arxiv.org/format/2206.10776">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Warm-Starting in Message Passing algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Skuratovs%2C+N">Nikolajs Skuratovs</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2206.10776v1-abstract-short" style="display: inline;"> Vector Approximate Message Passing (VAMP) provides the means of solving a linear inverse problem in a Bayes-optimal way assuming the measurement operator is sufficiently random. However, VAMP requires implementing the linear minimum mean squared error (LMMSE) estimator at every iteration, which makes the algorithm intractable for large-scale problems. In this work, we present a class of warm-start… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.10776v1-abstract-full').style.display = 'inline'; document.getElementById('2206.10776v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2206.10776v1-abstract-full" style="display: none;"> Vector Approximate Message Passing (VAMP) provides the means of solving a linear inverse problem in a Bayes-optimal way assuming the measurement operator is sufficiently random. However, VAMP requires implementing the linear minimum mean squared error (LMMSE) estimator at every iteration, which makes the algorithm intractable for large-scale problems. In this work, we present a class of warm-started (WS) methods that provides a scalable approximation of LMMSE within VAMP. We show that a Message Passing (MP) algorithm equipped with a method from this class can converge to the fixed point of VAMP while having a per-iteration computational complexity proportional to that of AMP. Additionally, we provide the Onsager correction and a multi-dimensional State Evolution for MP utilizing one of the WS methods. Lastly, we show that the approximation approach used in the recently proposed Memory AMP (MAMP) algorithm is a special case of the developed class of WS methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2206.10776v1-abstract-full').style.display = 'none'; document.getElementById('2206.10776v1-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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 for the ISIT conference 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/2203.16165">arXiv:2203.16165</a> <span> [<a href="https://arxiv.org/pdf/2203.16165">pdf</a>, <a href="https://arxiv.org/format/2203.16165">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</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/ACCESS.2022.3169744">10.1109/ACCESS.2022.3169744 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Symbolic music generation conditioned on continuous-valued emotions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sulun%2C+S">Serkan Sulun</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</a>, <a href="/search/cs?searchtype=author&query=Viana%2C+P">Paula Viana</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="2203.16165v2-abstract-short" style="display: inline;"> In this paper we present a new approach for the generation of multi-instrument symbolic music driven by musical emotion. The principal novelty of our approach centres on conditioning a state-of-the-art transformer based on continuous-valued valence and arousal labels. In addition, we provide a new large-scale dataset of symbolic music paired with emotion labels in terms of valence and arousal. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.16165v2-abstract-full').style.display = 'inline'; document.getElementById('2203.16165v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.16165v2-abstract-full" style="display: none;"> In this paper we present a new approach for the generation of multi-instrument symbolic music driven by musical emotion. The principal novelty of our approach centres on conditioning a state-of-the-art transformer based on continuous-valued valence and arousal labels. In addition, we provide a new large-scale dataset of symbolic music paired with emotion labels in terms of valence and arousal. We evaluate our approach in a quantitative manner in two ways, first by measuring its note prediction accuracy, and second via a regression task in the valence-arousal plane. Our results demonstrate that our proposed approaches outperform conditioning using control tokens which is representative of the current state of the art. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.16165v2-abstract-full').style.display = 'none'; document.getElementById('2203.16165v2-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 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">Published in IEEE Access</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> volume:10, year:2022, pages:44617-44626 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.00952">arXiv:2203.00952</a> <span> [<a href="https://arxiv.org/pdf/2203.00952">pdf</a>, <a href="https://arxiv.org/format/2203.00952">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Sketched RT3D: How to reconstruct billions of photons per second </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Tachella%2C+J">Juli谩n Tachella</a>, <a href="/search/cs?searchtype=author&query=Sheehan%2C+M+P">Michael P. Sheehan</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="2203.00952v1-abstract-short" style="display: inline;"> Single-photon light detection and ranging (lidar) captures depth and intensity information of a 3D scene. Reconstructing a scene from observed photons is a challenging task due to spurious detections associated with background illumination sources. To tackle this problem, there is a plethora of 3D reconstruction algorithms which exploit spatial regularity of natural scenes to provide stable recons… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.00952v1-abstract-full').style.display = 'inline'; document.getElementById('2203.00952v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.00952v1-abstract-full" style="display: none;"> Single-photon light detection and ranging (lidar) captures depth and intensity information of a 3D scene. Reconstructing a scene from observed photons is a challenging task due to spurious detections associated with background illumination sources. To tackle this problem, there is a plethora of 3D reconstruction algorithms which exploit spatial regularity of natural scenes to provide stable reconstructions. However, most existing algorithms have computational and memory complexity proportional to the number of recorded photons. This complexity hinders their real-time deployment on modern lidar arrays which acquire billions of photons per second. Leveraging a recent lidar sketching framework, we show that it is possible to modify existing reconstruction algorithms such that they only require a small sketch of the photon information. In particular, we propose a sketched version of a recent state-of-the-art algorithm which uses point cloud denoisers to provide spatially regularized reconstructions. A series of experiments performed on real lidar datasets demonstrates a significant reduction of execution time and memory requirements, while achieving the same reconstruction performance than in the full data case. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.00952v1-abstract-full').style.display = 'none'; document.getElementById('2203.00952v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 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">Accepted at ICASSP 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/2111.12855">arXiv:2111.12855</a> <span> [<a href="https://arxiv.org/pdf/2111.12855">pdf</a>, <a href="https://arxiv.org/format/2111.12855">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Tachella%2C+J">Juli谩n Tachella</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="2111.12855v2-abstract-short" style="display: inline;"> Deep networks provide state-of-the-art performance in multiple imaging inverse problems ranging from medical imaging to computational photography. However, most existing networks are trained with clean signals which are often hard or impossible to obtain. Equivariant imaging (EI) is a recent self-supervised learning framework that exploits the group invariance present in signal distributions to le… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.12855v2-abstract-full').style.display = 'inline'; document.getElementById('2111.12855v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.12855v2-abstract-full" style="display: none;"> Deep networks provide state-of-the-art performance in multiple imaging inverse problems ranging from medical imaging to computational photography. However, most existing networks are trained with clean signals which are often hard or impossible to obtain. Equivariant imaging (EI) is a recent self-supervised learning framework that exploits the group invariance present in signal distributions to learn a reconstruction function from partial measurement data alone. While EI results are impressive, its performance degrades with increasing noise. In this paper, we propose a Robust Equivariant Imaging (REI) framework which can learn to image from noisy partial measurements alone. The proposed method uses Stein's Unbiased Risk Estimator (SURE) to obtain a fully unsupervised training loss that is robust to noise. We show that REI leads to considerable performance gains on linear and nonlinear inverse problems, thereby paving the way for robust unsupervised imaging with deep networks. Code is available at: https://github.com/edongdongchen/REI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.12855v2-abstract-full').style.display = 'none'; document.getElementById('2111.12855v2-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 March, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">CVPR 2022. Code: https://github.com/edongdongchen/REI</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.08045">arXiv:2110.08045</a> <span> [<a href="https://arxiv.org/pdf/2110.08045">pdf</a>, <a href="https://arxiv.org/ps/2110.08045">ps</a>, <a href="https://arxiv.org/format/2110.08045">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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Compressive Independent Component Analysis: Theory and Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sheehan%2C+M+P">Michael P. Sheehan</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="2110.08045v1-abstract-short" style="display: inline;"> Compressive learning forms the exciting intersection between compressed sensing and statistical learning where one exploits forms of sparsity and structure to reduce the memory and/or computational complexity of the learning task. In this paper, we look at the independent component analysis (ICA) model through the compressive learning lens. In particular, we show that solutions to the cumulant bas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.08045v1-abstract-full').style.display = 'inline'; document.getElementById('2110.08045v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.08045v1-abstract-full" style="display: none;"> Compressive learning forms the exciting intersection between compressed sensing and statistical learning where one exploits forms of sparsity and structure to reduce the memory and/or computational complexity of the learning task. In this paper, we look at the independent component analysis (ICA) model through the compressive learning lens. In particular, we show that solutions to the cumulant based ICA model have particular structure that induces a low dimensional model set that resides in the cumulant tensor space. By showing a restricted isometry property holds for random cumulants e.g. Gaussian ensembles, we prove the existence of a compressive ICA scheme. Thereafter, we propose two algorithms of the form of an iterative projection gradient (IPG) and an alternating steepest descent (ASD) algorithm for compressive ICA, where the order of compression asserted from the restricted isometry property is realised through empirical results. We provide analysis of the CICA algorithms including the effects of finite samples. The effects of compression are characterised by a trade-off between the sketch size and the statistical efficiency of the ICA estimates. By considering synthetic and real datasets, we show the substantial memory gains achieved over well-known ICA algorithms by using one of the proposed CICA algorithms. Finally, we conclude the paper with open problems including interesting challenges from the emerging field of compressive learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.08045v1-abstract-full').style.display = 'none'; document.getElementById('2110.08045v1-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 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">27 pages, 8 figures, under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.14756">arXiv:2103.14756</a> <span> [<a href="https://arxiv.org/pdf/2103.14756">pdf</a>, <a href="https://arxiv.org/format/2103.14756">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Equivariant Imaging: Learning Beyond the Range Space </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Tachella%2C+J">Juli谩n Tachella</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2103.14756v2-abstract-short" style="display: inline;"> In various imaging problems, we only have access to compressed measurements of the underlying signals, hindering most learning-based strategies which usually require pairs of signals and associated measurements for training. Learning only from compressed measurements is impossible in general, as the compressed observations do not contain information outside the range of the forward sensing operato… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.14756v2-abstract-full').style.display = 'inline'; document.getElementById('2103.14756v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.14756v2-abstract-full" style="display: none;"> In various imaging problems, we only have access to compressed measurements of the underlying signals, hindering most learning-based strategies which usually require pairs of signals and associated measurements for training. Learning only from compressed measurements is impossible in general, as the compressed observations do not contain information outside the range of the forward sensing operator. We propose a new end-to-end self-supervised framework that overcomes this limitation by exploiting the equivariances present in natural signals. Our proposed learning strategy performs as well as fully supervised methods. Experiments demonstrate the potential of this framework on inverse problems including sparse-view X-ray computed tomography on real clinical data and image inpainting on natural images. Code has been made available at: https://github.com/edongdongchen/EI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.14756v2-abstract-full').style.display = 'none'; document.getElementById('2103.14756v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">ICCV 2021. Code: https://github.com/edongdongchen/EI</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.14690">arXiv:2012.14690</a> <span> [<a href="https://arxiv.org/pdf/2012.14690">pdf</a>, <a href="https://arxiv.org/format/2012.14690">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> COIN: Contrastive Identifier Network for Breast Mass Diagnosis in Mammography </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+H">Heyi Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Nailon%2C+W+H">William H. Nailon</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Laurenson%2C+D">David Laurenson</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2012.14690v1-abstract-short" style="display: inline;"> Computer-aided breast cancer diagnosis in mammography is a challenging problem, stemming from mammographical data scarcity and data entanglement. In particular, data scarcity is attributed to the privacy and expensive annotation. And data entanglement is due to the high similarity between benign and malignant masses, of which manifolds reside in lower dimensional space with very small margin. To a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.14690v1-abstract-full').style.display = 'inline'; document.getElementById('2012.14690v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.14690v1-abstract-full" style="display: none;"> Computer-aided breast cancer diagnosis in mammography is a challenging problem, stemming from mammographical data scarcity and data entanglement. In particular, data scarcity is attributed to the privacy and expensive annotation. And data entanglement is due to the high similarity between benign and malignant masses, of which manifolds reside in lower dimensional space with very small margin. To address these two challenges, we propose a deep learning framework, named Contrastive Identifier Network (\textsc{COIN}), which integrates adversarial augmentation and manifold-based contrastive learning. Firstly, we employ adversarial learning to create both on- and off-distribution mass contained ROIs. After that, we propose a novel contrastive loss with a built Signed graph. Finally, the neural network is optimized in a contrastive learning manner, with the purpose of improving the deep model's discriminativity on the extended dataset. In particular, by employing COIN, data samples from the same category are pulled close whereas those with different labels are pushed further in the deep latent space. Moreover, COIN outperforms the state-of-the-art related algorithms for solving breast cancer diagnosis problem by a considerable margin, achieving 93.4\% accuracy and 95.0\% AUC score. The code will release on ***. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.14690v1-abstract-full').style.display = 'none'; document.getElementById('2012.14690v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.07274">arXiv:2011.07274</a> <span> [<a href="https://arxiv.org/pdf/2011.07274">pdf</a>, <a href="https://arxiv.org/format/2011.07274">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</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/JSTSP.2020.3037485">10.1109/JSTSP.2020.3037485 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sulun%2C+S">Serkan Sulun</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2011.07274v2-abstract-short" style="display: inline;"> In this paper, we address a sub-topic of the broad domain of audio enhancement, namely musical audio bandwidth extension. We formulate the bandwidth extension problem using deep neural networks, where a band-limited signal is provided as input to the network, with the goal of reconstructing a full-bandwidth output. Our main contribution centers on the impact of the choice of low pass filter when t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.07274v2-abstract-full').style.display = 'inline'; document.getElementById('2011.07274v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.07274v2-abstract-full" style="display: none;"> In this paper, we address a sub-topic of the broad domain of audio enhancement, namely musical audio bandwidth extension. We formulate the bandwidth extension problem using deep neural networks, where a band-limited signal is provided as input to the network, with the goal of reconstructing a full-bandwidth output. Our main contribution centers on the impact of the choice of low pass filter when training and subsequently testing the network. For two different state of the art deep architectures, ResNet and U-Net, we demonstrate that when the training and testing filters are matched, improvements in signal-to-noise ratio (SNR) of up to 7dB can be obtained. However, when these filters differ, the improvement falls considerably and under some training conditions results in a lower SNR than the band-limited input. To circumvent this apparent overfitting to filter shape, we propose a data augmentation strategy which utilizes multiple low pass filters during training and leads to improved generalization to unseen filtering conditions at test time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.07274v2-abstract-full').style.display = 'none'; document.getElementById('2011.07274v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Qualitative examples on https://serkansulun.com/bwe. Source code on https://github.com/serkansulun/deep-music-enhancer</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2011.01637">arXiv:2011.01637</a> <span> [<a href="https://arxiv.org/pdf/2011.01637">pdf</a>, <a href="https://arxiv.org/format/2011.01637">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Shift If You Can: Counting and Visualising Correction Operations for Beat Tracking Evaluation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pinto%2C+A+S">A. S谩 Pinto</a>, <a href="/search/cs?searchtype=author&query=Domingues%2C+I">I. Domingues</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">M. E. P. Davies</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2011.01637v1-abstract-short" style="display: inline;"> In this late-breaking abstract we propose a modified approach for beat tracking evaluation which poses the problem in terms of the effort required to transform a sequence of beat detections such that they maximise the well-known F-measure calculation when compared to a sequence of ground truth annotations. Central to our approach is the inclusion of a shifting operation conducted over an additiona… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.01637v1-abstract-full').style.display = 'inline'; document.getElementById('2011.01637v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2011.01637v1-abstract-full" style="display: none;"> In this late-breaking abstract we propose a modified approach for beat tracking evaluation which poses the problem in terms of the effort required to transform a sequence of beat detections such that they maximise the well-known F-measure calculation when compared to a sequence of ground truth annotations. Central to our approach is the inclusion of a shifting operation conducted over an additional, larger, tolerance window, which can substitute the combination of insertions and deletions. We describe a straightforward calculation of annotation efficiency and combine this with an informative visualisation which can be of use for the qualitative evaluation of beat tracking systems. We make our implementation and visualisation code freely available in a GitHub repository. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2011.01637v1-abstract-full').style.display = 'none'; document.getElementById('2011.01637v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ISMIR 2020 Late Breaking/Demo</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2008.11529">arXiv:2008.11529</a> <span> [<a href="https://arxiv.org/pdf/2008.11529">pdf</a>, <a href="https://arxiv.org/format/2008.11529">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> TIV.lib: an open-source library for the tonal description of musical audio </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ramires%2C+A">Ant贸nio Ramires</a>, <a href="/search/cs?searchtype=author&query=Bernardes%2C+G">Gilberto Bernardes</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</a>, <a href="/search/cs?searchtype=author&query=Serra%2C+X">Xavier Serra</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2008.11529v1-abstract-short" style="display: inline;"> In this paper, we present TIV.lib, an open-source library for the content-based tonal description of musical audio signals. Its main novelty relies on the perceptually-inspired Tonal Interval Vector space based on the Discrete Fourier transform, from which multiple instantaneous and global representations, descriptors and metrics are computed - e.g., harmonic change, dissonance, diatonicity, and m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.11529v1-abstract-full').style.display = 'inline'; document.getElementById('2008.11529v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.11529v1-abstract-full" style="display: none;"> In this paper, we present TIV.lib, an open-source library for the content-based tonal description of musical audio signals. Its main novelty relies on the perceptually-inspired Tonal Interval Vector space based on the Discrete Fourier transform, from which multiple instantaneous and global representations, descriptors and metrics are computed - e.g., harmonic change, dissonance, diatonicity, and musical key. The library is cross-platform, implemented in Python and the graphical programming language Pure Data, and can be used in both online and offline scenarios. Of note is its potential for enhanced Music Information Retrieval, where tonal descriptors sit at the core of numerous methods and applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.11529v1-abstract-full').style.display = 'none'; document.getElementById('2008.11529v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2008.02957">arXiv:2008.02957</a> <span> [<a href="https://arxiv.org/pdf/2008.02957">pdf</a>, <a href="https://arxiv.org/ps/2008.02957">ps</a>, <a href="https://arxiv.org/format/2008.02957">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Dual Convolutional Neural Networks for Breast Mass Segmentation and Diagnosis in Mammography </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+H">Heyi Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Nailon%2C+W+H">William H. Nailon</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Laurenson%2C+D">David Laurenson</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2008.02957v2-abstract-short" style="display: inline;"> Deep convolutional neural networks (CNNs) have emerged as a new paradigm for Mammogram diagnosis. Contemporary CNN-based computer-aided-diagnosis (CAD) for breast cancer directly extract latent features from input mammogram image and ignore the importance of morphological features. In this paper, we introduce a novel deep learning framework for mammogram image processing, which computes mass segme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.02957v2-abstract-full').style.display = 'inline'; document.getElementById('2008.02957v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2008.02957v2-abstract-full" style="display: none;"> Deep convolutional neural networks (CNNs) have emerged as a new paradigm for Mammogram diagnosis. Contemporary CNN-based computer-aided-diagnosis (CAD) for breast cancer directly extract latent features from input mammogram image and ignore the importance of morphological features. In this paper, we introduce a novel deep learning framework for mammogram image processing, which computes mass segmentation and simultaneously predict diagnosis results. Specifically, our method is constructed in a dual-path architecture that solves the mapping in a dual-problem manner, with an additional consideration of important shape and boundary knowledge. One path called the Locality Preserving Learner (LPL), is devoted to hierarchically extracting and exploiting intrinsic features of the input. Whereas the other path, called the Conditional Graph Learner (CGL) focuses on generating geometrical features via modeling pixel-wise image to mask correlations. By integrating the two learners, both the semantics and structure are well preserved and the component learning paths in return complement each other, contributing an improvement to the mass segmentation and cancer classification problem at the same time. We evaluated our method on two most used public mammography datasets, DDSM and INbreast. Experimental results show that DualCoreNet achieves the best mammography segmentation and classification simultaneously, outperforming recent state-of-the-art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2008.02957v2-abstract-full').style.display = 'none'; document.getElementById('2008.02957v2-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 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2007.14281">arXiv:2007.14281</a> <span> [<a href="https://arxiv.org/pdf/2007.14281">pdf</a>, <a href="https://arxiv.org/ps/2007.14281">ps</a>, <a href="https://arxiv.org/format/2007.14281">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> DeepMP for Non-Negative Sparse Decomposition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Voulgaris%2C+K+A">Konstantinos A. Voulgaris</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Yaghoobi%2C+M">Mehrdad Yaghoobi</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="2007.14281v1-abstract-short" style="display: inline;"> Non-negative signals form an important class of sparse signals. Many algorithms have already beenproposed to recover such non-negative representations, where greedy and convex relaxed algorithms are among the most popular methods. The greedy techniques are low computational cost algorithms, which have also been modified to incorporate the non-negativity of the representations. One such modificatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.14281v1-abstract-full').style.display = 'inline'; document.getElementById('2007.14281v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2007.14281v1-abstract-full" style="display: none;"> Non-negative signals form an important class of sparse signals. Many algorithms have already beenproposed to recover such non-negative representations, where greedy and convex relaxed algorithms are among the most popular methods. The greedy techniques are low computational cost algorithms, which have also been modified to incorporate the non-negativity of the representations. One such modification has been proposed for Matching Pursuit (MP) based algorithms, which first chooses positive coefficients and uses a non-negative optimisation technique that guarantees the non-negativity of the coefficients. The performance of greedy algorithms, like all non-exhaustive search methods, suffer from high coherence with the linear generative model, called the dictionary. We here first reformulate the non-negative matching pursuit algorithm in the form of a deep neural network. We then show that the proposed model after training yields a significant improvement in terms of exact recovery performance, compared to other non-trained greedy algorithms, while keeping the complexity low. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2007.14281v1-abstract-full').style.display = 'none'; document.getElementById('2007.14281v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.15271">arXiv:2006.15271</a> <span> [<a href="https://arxiv.org/pdf/2006.15271">pdf</a>, <a href="https://arxiv.org/format/2006.15271">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Golbabaee%2C+M">Mohammad Golbabaee</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="2006.15271v3-abstract-short" style="display: inline;"> Consistency of the predictions with respect to the physical forward model is pivotal for reliably solving inverse problems. This consistency is mostly un-controlled in the current end-to-end deep learning methodologies proposed for the Magnetic Resonance Fingerprinting (MRF) problem. To address this, we propose ProxNet, a learned proximal gradient descent framework that directly incorporates the f… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.15271v3-abstract-full').style.display = 'inline'; document.getElementById('2006.15271v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.15271v3-abstract-full" style="display: none;"> Consistency of the predictions with respect to the physical forward model is pivotal for reliably solving inverse problems. This consistency is mostly un-controlled in the current end-to-end deep learning methodologies proposed for the Magnetic Resonance Fingerprinting (MRF) problem. To address this, we propose ProxNet, a learned proximal gradient descent framework that directly incorporates the forward acquisition and Bloch dynamic models within a recurrent learning mechanism. The ProxNet adopts a compact neural proximal model for de-aliasing and quantitative inference, that can be flexibly trained on scarce MRF training datasets. Our numerical experiments show that the ProxNet can achieve a superior quantitative inference accuracy, much smaller storage requirement, and a comparable runtime to the recent deep learning MRF baselines, while being much faster than the dictionary matching schemes. Code has been released at https://github.com/edongdongchen/PGD-Net. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.15271v3-abstract-full').style.display = 'none'; document.getElementById('2006.15271v3-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 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in MICCAI 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.09211">arXiv:2004.09211</a> <span> [<a href="https://arxiv.org/pdf/2004.09211">pdf</a>, <a href="https://arxiv.org/format/2004.09211">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</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/TIP.2020.3046882">10.1109/TIP.2020.3046882 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Robust 3D reconstruction of dynamic scenes from single-photon lidar using Beta-divergences </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Legros%2C+Q">Quentin Legros</a>, <a href="/search/cs?searchtype=author&query=Tachella%2C+J">Julian Tachella</a>, <a href="/search/cs?searchtype=author&query=Tobin%2C+R">Rachael Tobin</a>, <a href="/search/cs?searchtype=author&query=McCarthy%2C+A">Aongus McCarthy</a>, <a href="/search/cs?searchtype=author&query=Meignen%2C+S">Sylvain Meignen</a>, <a href="/search/cs?searchtype=author&query=Buller%2C+G+S">Gerald S. Buller</a>, <a href="/search/cs?searchtype=author&query=Altmann%2C+Y">Yoann Altmann</a>, <a href="/search/cs?searchtype=author&query=McLaughlin%2C+S">Stephen McLaughlin</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Michael E. Davies</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="2004.09211v3-abstract-short" style="display: inline;"> In this paper, we present a new algorithm for fast, online 3D reconstruction of dynamic scenes using times of arrival of photons recorded by single-photon detector arrays. One of the main challenges in 3D imaging using single-photon lidar in practical applications is the presence of strong ambient illumination which corrupts the data and can jeopardize the detection of peaks/surface in the signals… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.09211v3-abstract-full').style.display = 'inline'; document.getElementById('2004.09211v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.09211v3-abstract-full" style="display: none;"> In this paper, we present a new algorithm for fast, online 3D reconstruction of dynamic scenes using times of arrival of photons recorded by single-photon detector arrays. One of the main challenges in 3D imaging using single-photon lidar in practical applications is the presence of strong ambient illumination which corrupts the data and can jeopardize the detection of peaks/surface in the signals. This background noise not only complicates the observation model classically used for 3D reconstruction but also the estimation procedure which requires iterative methods. In this work, we consider a new similarity measure for robust depth estimation, which allows us to use a simple observation model and a non-iterative estimation procedure while being robust to mis-specification of the background illumination model. This choice leads to a computationally attractive depth estimation procedure without significant degradation of the reconstruction performance. This new depth estimation procedure is coupled with a spatio-temporal model to capture the natural correlation between neighboring pixels and successive frames for dynamic scene analysis. The resulting online inference process is scalable and well suited for parallel implementation. The benefits of the proposed method are demonstrated through a series of experiments conducted with simulated and real single-photon lidar videos, allowing the analysis of dynamic scenes at 325 m observed under extreme ambient illumination conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.09211v3-abstract-full').style.display = 'none'; document.getElementById('2004.09211v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1912.02880">arXiv:1912.02880</a> <span> [<a href="https://arxiv.org/pdf/1912.02880">pdf</a>, <a href="https://arxiv.org/ps/1912.02880">ps</a>, <a href="https://arxiv.org/format/1912.02880">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div 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/LSP.2020.2973506">10.1109/LSP.2020.2973506 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> (l1,l2)-RIP and Projected Back-Projection Reconstruction for Phase-Only Measurements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feuillen%2C+T">Thomas Feuillen</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Vandendorpe%2C+L">Luc Vandendorpe</a>, <a href="/search/cs?searchtype=author&query=Jacques%2C+L">Laurent Jacques</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1912.02880v1-abstract-short" style="display: inline;"> This letter analyzes the performances of a simple reconstruction method, namely the Projected Back-Projection (PBP), for estimating the direction of a sparse signal from its phase-only (or amplitude-less) complex Gaussian random measurements, i.e., an extension of one-bit compressive sensing to the complex field. To study the performances of this algorithm, we show that complex Gaussian random mat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.02880v1-abstract-full').style.display = 'inline'; document.getElementById('1912.02880v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1912.02880v1-abstract-full" style="display: none;"> This letter analyzes the performances of a simple reconstruction method, namely the Projected Back-Projection (PBP), for estimating the direction of a sparse signal from its phase-only (or amplitude-less) complex Gaussian random measurements, i.e., an extension of one-bit compressive sensing to the complex field. To study the performances of this algorithm, we show that complex Gaussian random matrices respect, with high probability, a variant of the Restricted Isometry Property (RIP) relating to the l1 -norm of the sparse signal measurements to their l2 -norm. This property allows us to upper-bound the reconstruction error of PBP in the presence of phase noise. Monte Carlo simulations are performed to highlight the performance of our approach in this phase-only acquisition model when compared to error achieved by PBP in classical compressive sensing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1912.02880v1-abstract-full').style.display = 'none'; document.getElementById('1912.02880v1-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 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">4 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.11028">arXiv:1911.11028</a> <span> [<a href="https://arxiv.org/pdf/1911.11028">pdf</a>, <a href="https://arxiv.org/format/1911.11028">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Deep Decomposition Learning for Inverse Imaging Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1911.11028v3-abstract-short" style="display: inline;"> Deep learning is emerging as a new paradigm for solving inverse imaging problems. However, the deep learning methods often lack the assurance of traditional physics-based methods due to the lack of physical information considerations in neural network training and deploying. The appropriate supervision and explicit calibration by the information of the physic model can enhance the neural network l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.11028v3-abstract-full').style.display = 'inline'; document.getElementById('1911.11028v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.11028v3-abstract-full" style="display: none;"> Deep learning is emerging as a new paradigm for solving inverse imaging problems. However, the deep learning methods often lack the assurance of traditional physics-based methods due to the lack of physical information considerations in neural network training and deploying. The appropriate supervision and explicit calibration by the information of the physic model can enhance the neural network learning and its practical performance. In this paper, inspired by the geometry that data can be decomposed by two components from the null-space of the forward operator and the range space of its pseudo-inverse, we train neural networks to learn the two components and therefore learn the decomposition, i.e. we explicitly reformulate the neural network layers as learning range-nullspace decomposition functions with reference to the layer inputs, instead of learning unreferenced functions. We empirically show that the proposed framework demonstrates superior performance over recent deep residual learning, unrolled learning and nullspace learning on tasks including compressive sensing medical imaging and natural image super-resolution. Our code is available at https://github.com/edongdongchen/DDN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.11028v3-abstract-full').style.display = 'none'; document.getElementById('1911.11028v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 July, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in ECCV 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1910.10024">arXiv:1910.10024</a> <span> [<a href="https://arxiv.org/pdf/1910.10024">pdf</a>, <a href="https://arxiv.org/format/1910.10024">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"> Compressive Learning for Semi-Parametric Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sheehan%2C+M+P">Michael P. Sheehan</a>, <a href="/search/cs?searchtype=author&query=Gonon%2C+A">Antoine Gonon</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1910.10024v1-abstract-short" style="display: inline;"> In the compressive learning theory, instead of solving a statistical learning problem from the input data, a so-called sketch is computed from the data prior to learning. The sketch has to capture enough information to solve the problem directly from it, allowing to discard the dataset from the memory. This is useful when dealing with large datasets as the size of the sketch does not scale with th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.10024v1-abstract-full').style.display = 'inline'; document.getElementById('1910.10024v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1910.10024v1-abstract-full" style="display: none;"> In the compressive learning theory, instead of solving a statistical learning problem from the input data, a so-called sketch is computed from the data prior to learning. The sketch has to capture enough information to solve the problem directly from it, allowing to discard the dataset from the memory. This is useful when dealing with large datasets as the size of the sketch does not scale with the size of the database. In this paper, we reformulate the original compressive learning framework to explicitly cater for the class of semi-parametric models. The reformulation takes account of the inherent topology and structure of semi-parametric models, creating an intuitive pathway to the development of compressive learning algorithms. We apply our developed framework to both the semi-parametric models of independent component analysis and subspace clustering, demonstrating the robustness of the framework to explicitly show when a compression in complexity can be achieved. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.10024v1-abstract-full').style.display = 'none'; document.getElementById('1910.10024v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 5 figure, submitted to ICASSP 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1907.00300">arXiv:1907.00300</a> <span> [<a href="https://arxiv.org/pdf/1907.00300">pdf</a>, <a href="https://arxiv.org/format/1907.00300">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Signed Laplacian Deep Learning with Adversarial Augmentation for Improved Mammography Diagnosis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+H">Heyi Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Nailon%2C+W+H">William H. Nailon</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Laurenson%2C+D+I">David I. Laurenson</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="1907.00300v2-abstract-short" style="display: inline;"> Computer-aided breast cancer diagnosis in mammography is limited by inadequate data and the similarity between benign and cancerous masses. To address this, we propose a signed graph regularized deep neural network with adversarial augmentation, named \textsc{DiagNet}. Firstly, we use adversarial learning to generate positive and negative mass-contained mammograms for each mass class. After that,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.00300v2-abstract-full').style.display = 'inline'; document.getElementById('1907.00300v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1907.00300v2-abstract-full" style="display: none;"> Computer-aided breast cancer diagnosis in mammography is limited by inadequate data and the similarity between benign and cancerous masses. To address this, we propose a signed graph regularized deep neural network with adversarial augmentation, named \textsc{DiagNet}. Firstly, we use adversarial learning to generate positive and negative mass-contained mammograms for each mass class. After that, a signed similarity graph is built upon the expanded data to further highlight the discrimination. Finally, a deep convolutional neural network is trained by jointly optimizing the signed graph regularization and classification loss. Experiments show that the \textsc{DiagNet} framework outperforms the state-of-the-art in breast mass diagnosis in mammography. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.00300v2-abstract-full').style.display = 'none'; document.getElementById('1907.00300v2-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 September, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in MICCAI October 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1903.00001">arXiv:1903.00001</a> <span> [<a href="https://arxiv.org/pdf/1903.00001">pdf</a>, <a href="https://arxiv.org/ps/1903.00001">ps</a>, <a href="https://arxiv.org/format/1903.00001">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> A Deep DUAL-PATH Network for Improved Mammogram Image Processing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+H">Heyi Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Nailon%2C+W+H">William H. Nailon</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Laurenson%2C+D">Dave Laurenson</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="1903.00001v1-abstract-short" style="display: inline;"> We present, for the first time, a novel deep neural network architecture called \dcn with a dual-path connection between the input image and output class label for mammogram image processing. This architecture is built upon U-Net, which non-linearly maps the input data into a deep latent space. One path of the \dcnn, the locality preserving learner, is devoted to hierarchically extracting and expl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.00001v1-abstract-full').style.display = 'inline'; document.getElementById('1903.00001v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1903.00001v1-abstract-full" style="display: none;"> We present, for the first time, a novel deep neural network architecture called \dcn with a dual-path connection between the input image and output class label for mammogram image processing. This architecture is built upon U-Net, which non-linearly maps the input data into a deep latent space. One path of the \dcnn, the locality preserving learner, is devoted to hierarchically extracting and exploiting intrinsic features of the input, while the other path, called the conditional graph learner, focuses on modeling the input-mask correlations. The learned mask is further used to improve classification results, and the two learning paths complement each other. By integrating the two learners our new architecture provides a simple but effective way to jointly learn the segmentation and predict the class label. Benefiting from the powerful expressive capacity of deep neural networks a more discriminative representation can be learned, in which both the semantics and structure are well preserved. Experimental results show that \dcn achieves the best mammography segmentation and classification simultaneously, outperforming recent state-of-the-art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1903.00001v1-abstract-full').style.display = 'none'; document.getElementById('1903.00001v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To Appear in ICCASP 2019 May</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.04493">arXiv:1811.04493</a> <span> [<a href="https://arxiv.org/pdf/1811.04493">pdf</a>, <a href="https://arxiv.org/format/1811.04493">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> </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.acha.2022.03.002">10.1016/j.acha.2022.03.002 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Analysis vs Synthesis with Structure - An Investigation of Union of Subspace Models on Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kotzagiannidis%2C+M+S">Madeleine S. Kotzagiannidis</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1811.04493v1-abstract-short" style="display: inline;"> We consider the problem of characterizing the `duality gap' between sparse synthesis- and cosparse analysis-driven signal models through the lens of spectral graph theory, in an effort to comprehend their precise equivalencies and discrepancies. By detecting and exploiting the inherent connectivity structure, and hence, distinct set of properties, of rank-deficient graph difference matrices such a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.04493v1-abstract-full').style.display = 'inline'; document.getElementById('1811.04493v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.04493v1-abstract-full" style="display: none;"> We consider the problem of characterizing the `duality gap' between sparse synthesis- and cosparse analysis-driven signal models through the lens of spectral graph theory, in an effort to comprehend their precise equivalencies and discrepancies. By detecting and exploiting the inherent connectivity structure, and hence, distinct set of properties, of rank-deficient graph difference matrices such as the graph Laplacian, we are able to substantiate discrepancies between the cosparse analysis and sparse synthesis models, according to which the former constitutes a constrained and translated instance of the latter. In view of a general union of subspaces model, we conduct a study of the associated subspaces and their composition, which further facilitates the refinement of specialized uniqueness and recovery guarantees, and discover an underlying structured sparsity model based on the graph incidence matrix. Furthermore, for circulant graphs, we provide an exact characterization of underlying subspaces by deriving closed-form expressions as well as demonstrating transitional properties between equivalence and non-equivalence for a parametric generalization of the graph Laplacian. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.04493v1-abstract-full').style.display = 'none'; document.getElementById('1811.04493v1-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 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.04460">arXiv:1811.04460</a> <span> [<a href="https://arxiv.org/pdf/1811.04460">pdf</a>, <a href="https://arxiv.org/format/1811.04460">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Discrete Mathematics">cs.DM</span> </div> </div> <p class="title is-5 mathjax"> Analysis vs Synthesis - An Investigation of (Co)sparse Signal Models on Graphs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kotzagiannidis%2C+M+S">Madeleine S. Kotzagiannidis</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1811.04460v1-abstract-short" style="display: inline;"> In this work, we present a theoretical study of signals with sparse representations in the vertex domain of a graph, which is primarily motivated by the discrepancy arising from respectively adopting a synthesis and analysis view of the graph Laplacian matrix. Sparsity on graphs and, in particular, the characterization of the subspaces of signals which are sparse with respect to the connectivity o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.04460v1-abstract-full').style.display = 'inline'; document.getElementById('1811.04460v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.04460v1-abstract-full" style="display: none;"> In this work, we present a theoretical study of signals with sparse representations in the vertex domain of a graph, which is primarily motivated by the discrepancy arising from respectively adopting a synthesis and analysis view of the graph Laplacian matrix. Sparsity on graphs and, in particular, the characterization of the subspaces of signals which are sparse with respect to the connectivity of the graph, as induced by analysis with a suitable graph operator, remains in general an opaque concept which we aim to elucidate. By leveraging the theory of cosparsity, we present a novel (co)sparse graph Laplacian-based signal model and characterize the underlying (structured) (co)sparsity, smoothness and localization of its solution subspaces on undirected graphs, while providing more refined statements for special cases such as circulant graphs. Ultimately, we substantiate fundamental discrepancies between the cosparse analysis and sparse synthesis models in this structured setting, by demonstrating that the former constitutes a special, constrained instance of the latter. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.04460v1-abstract-full').style.display = 'none'; document.getElementById('1811.04460v1-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 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2018. </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">IEEE GlobalSIP 2018. An extended version of this work can be found at arXiv:1811.04493</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.02411">arXiv:1811.02411</a> <span> [<a href="https://arxiv.org/pdf/1811.02411">pdf</a>, <a href="https://arxiv.org/format/1811.02411">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> An audio-only method for advertisement detection in broadcast television content </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ramires%2C+A">Ant贸nio Ramires</a>, <a href="/search/cs?searchtype=author&query=Cocharro%2C+D">Diogo Cocharro</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</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="1811.02411v1-abstract-short" style="display: inline;"> We address the task of advertisement detection in broadcast television content. While typically approached from a video-only or audio-visual perspective, we present an audio-only method. Our approach centres on the detection of short silences which exist at the boundaries between programming and advertising, as well as between the advertisements themselves. To identify advertising regions we first… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.02411v1-abstract-full').style.display = 'inline'; document.getElementById('1811.02411v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.02411v1-abstract-full" style="display: none;"> We address the task of advertisement detection in broadcast television content. While typically approached from a video-only or audio-visual perspective, we present an audio-only method. Our approach centres on the detection of short silences which exist at the boundaries between programming and advertising, as well as between the advertisements themselves. To identify advertising regions we first locate all points within the broadcast content with very low signal energy. Next, we use a multiple linear regression model to reject non-boundary silences based on features extracted from the local context immediately surrounding the silence. Finally, we determine the advertising regions based on the long-term grouping of detected boundary silences. When evaluated over a 26 hour annotated database covering national and commercial Portuguese television channels we obtain a Matthews correlation coefficient in excess of 0.87 and outperform a freely available audio-visual approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.02411v1-abstract-full').style.display = 'none'; document.getElementById('1811.02411v1-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 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proc. of RecPad-2017, Amadora, Portugal, pp. 21-22, October, 2017 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1811.02406">arXiv:1811.02406</a> <span> [<a href="https://arxiv.org/pdf/1811.02406">pdf</a>, <a href="https://arxiv.org/format/1811.02406">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> User Specific Adaptation in Automatic Transcription of Vocalised Percussion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ramires%2C+A">Ant贸nio Ramires</a>, <a href="/search/cs?searchtype=author&query=Penha%2C+R">Rui Penha</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E+P">Matthew E. P. Davies</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="1811.02406v1-abstract-short" style="display: inline;"> The goal of this work is to develop an application that enables music producers to use their voice to create drum patterns when composing in Digital Audio Workstations (DAWs). An easy-to-use and user-oriented system capable of automatically transcribing vocalisations of percussion sounds, called LVT - Live Vocalised Transcription, is presented. LVT is developed as a Max for Live device which follo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.02406v1-abstract-full').style.display = 'inline'; document.getElementById('1811.02406v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1811.02406v1-abstract-full" style="display: none;"> The goal of this work is to develop an application that enables music producers to use their voice to create drum patterns when composing in Digital Audio Workstations (DAWs). An easy-to-use and user-oriented system capable of automatically transcribing vocalisations of percussion sounds, called LVT - Live Vocalised Transcription, is presented. LVT is developed as a Max for Live device which follows the `segment-and-classify' methodology for drum transcription, and includes three modules: i) an onset detector to segment events in time; ii) a module that extracts relevant features from the audio content; and iii) a machine-learning component that implements the k-Nearest Neighbours (kNN) algorithm for the classification of vocalised drum timbres. Due to the wide differences in vocalisations from distinct users for the same drum sound, a user-specific approach to vocalised transcription is proposed. In this perspective, a given end-user trains the algorithm with their own vocalisations for each drum sound before inputting their desired pattern into the DAW. The user adaption is achieved via a new Max external which implements Sequential Forward Selection (SFS) for choosing the most relevant features for a given set of input drum sounds. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1811.02406v1-abstract-full').style.display = 'none'; document.getElementById('1811.02406v1-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 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proc. of RecPad-2017, Amadora, Portugal, pp. 19-20, October, 2017 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1809.02506">arXiv:1809.02506</a> <span> [<a href="https://arxiv.org/pdf/1809.02506">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Balanced multi-shot EPI for accelerated Cartesian MRF: An alternative to spiral MRF </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Benjamin%2C+A+J+V">Arnold Julian Vinoj Benjamin</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+P+A">Pedro A. G贸mez</a>, <a href="/search/cs?searchtype=author&query=Golbabaee%2C+M">Mohammad Golbabaee</a>, <a href="/search/cs?searchtype=author&query=Sprenger%2C+T">Tim Sprenger</a>, <a href="/search/cs?searchtype=author&query=Menzel%2C+M+I">Marion I. Menzel</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Marshall%2C+I">Ian Marshall</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="1809.02506v1-abstract-short" style="display: inline;"> The main purpose of this study is to show that a highly accelerated Cartesian MRF scheme using a multi-shot EPI readout (i.e. multi-shot EPI-MRF) can produce good quality multi-parametric maps such as T1, T2 and proton density (PD) in a sufficiently short scan duration that is similar to conventional MRF. This multi-shot approach allows considerable subsampling while traversing the entire k-space… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.02506v1-abstract-full').style.display = 'inline'; document.getElementById('1809.02506v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1809.02506v1-abstract-full" style="display: none;"> The main purpose of this study is to show that a highly accelerated Cartesian MRF scheme using a multi-shot EPI readout (i.e. multi-shot EPI-MRF) can produce good quality multi-parametric maps such as T1, T2 and proton density (PD) in a sufficiently short scan duration that is similar to conventional MRF. This multi-shot approach allows considerable subsampling while traversing the entire k-space trajectory, can yield better SNR, reduced blurring, less distortion and can also be used to collect higher resolution data compared to existing single-shot EPI-MRF implementations. The generated parametric maps are compared to an accelerated spiral MRF implementation with the same acquisition parameters to evaluate the performance of this method. Additionally, an iterative reconstruction algorithm is applied to improve the accuracy of parametric map estimations and the fast convergence of EPI-MRF is also demonstrated. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.02506v1-abstract-full').style.display = 'none'; document.getElementById('1809.02506v1-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 September, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2018. </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">Proceedings of the Joint Annual Meeting ISMRM-ESMRMB 2018 - Paris</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1809.02503">arXiv:1809.02503</a> <span> [<a href="https://arxiv.org/pdf/1809.02503">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> CoverBLIP: scalable iterative matched filtering for MR Fingerprint recovery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Golbabaee%2C+M">Mohammad Golbabaee</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Z">Zhouye Chen</a>, <a href="/search/cs?searchtype=author&query=Wiaux%2C+Y">Yves Wiaux</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1809.02503v1-abstract-short" style="display: inline;"> Current proposed solutions for the high dimensionality of the MRF reconstruction problem rely on a linear compression step to reduce the matching computations and boost the efficiency of fast but non-scalable searching schemes such as the KD-trees. However such methodologies often introduce an unfavourable compromise in the estimation accuracy when applied to nonlinear data structures such as the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.02503v1-abstract-full').style.display = 'inline'; document.getElementById('1809.02503v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1809.02503v1-abstract-full" style="display: none;"> Current proposed solutions for the high dimensionality of the MRF reconstruction problem rely on a linear compression step to reduce the matching computations and boost the efficiency of fast but non-scalable searching schemes such as the KD-trees. However such methodologies often introduce an unfavourable compromise in the estimation accuracy when applied to nonlinear data structures such as the manifold of Bloch responses with possible increased dynamic complexity and growth in data population. To address this shortcoming we propose an inexact iterative reconstruction method, dubbed as the Cover BLoch response Iterative Projection (CoverBLIP). Iterative methods improve the accuracy of their non-iterative counterparts and are additionally robust against certain accelerated approximate updates, without compromising their final accuracy. Leveraging on these results, we accelerate matched-filtering using an ANNS algorithm based on Cover trees with a robustness feature against the curse of dimensionality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.02503v1-abstract-full').style.display = 'none'; document.getElementById('1809.02503v1-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 September, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2018. </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 Joint Annual Meeting ISMRM-ESMRMB 2018 - Paris</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1809.01749">arXiv:1809.01749</a> <span> [<a href="https://arxiv.org/pdf/1809.01749">pdf</a>, <a href="https://arxiv.org/format/1809.01749">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"> Geometry of Deep Learning for Magnetic Resonance Fingerprinting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Golbabaee%2C+M">Mohammad Golbabaee</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=G%C3%B3mez%2C+P+A">Pedro A. G贸mez</a>, <a href="/search/cs?searchtype=author&query=Menzel%2C+M+I">Marion I. Menzel</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1809.01749v2-abstract-short" style="display: inline;"> Current popular methods for Magnetic Resonance Fingerprint (MRF) recovery are bottlenecked by the heavy storage and computation requirements of a dictionary-matching (DM) step due to the growing size and complexity of the fingerprint dictionaries in multi-parametric quantitative MRI applications. In this paper we study a deep learning approach to address these shortcomings. Coupled with a dimensio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.01749v2-abstract-full').style.display = 'inline'; document.getElementById('1809.01749v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1809.01749v2-abstract-full" style="display: none;"> Current popular methods for Magnetic Resonance Fingerprint (MRF) recovery are bottlenecked by the heavy storage and computation requirements of a dictionary-matching (DM) step due to the growing size and complexity of the fingerprint dictionaries in multi-parametric quantitative MRI applications. In this paper we study a deep learning approach to address these shortcomings. Coupled with a dimensionality reduction first layer, the proposed MRF-Net is able to reconstruct quantitative maps by saving more than 60 times in memory and computations required for a DM baseline. Fine-grid manifold enumeration i.e. the MRF dictionary is only used for training the network and not during image reconstruction. We show that the MRF-Net provides a piece-wise affine approximation to the Bloch response manifold projection and that rather than memorizing the dictionary, the network efficiently clusters this manifold and learns a set of hierarchical matched-filters for affine regression of the NMR characteristics in each segment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.01749v2-abstract-full').style.display = 'none'; document.getElementById('1809.01749v2-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 November, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 September, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1808.09389">arXiv:1808.09389</a> <span> [<a href="https://arxiv.org/pdf/1808.09389">pdf</a>, <a href="https://arxiv.org/format/1808.09389">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"> Learning Discriminative Representation with Signed Laplacian Restricted Boltzmann Machine </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dongdong Chen</a>, <a href="/search/cs?searchtype=author&query=Lv%2C+J">Jiancheng Lv</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1808.09389v1-abstract-short" style="display: inline;"> We investigate the potential of a restricted Boltzmann Machine (RBM) for discriminative representation learning. By imposing the class information preservation constraints on the hidden layer of the RBM, we propose a Signed Laplacian Restricted Boltzmann Machine (SLRBM) for supervised discriminative representation learning. The model utilizes the label information and preserves the global data loc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1808.09389v1-abstract-full').style.display = 'inline'; document.getElementById('1808.09389v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1808.09389v1-abstract-full" style="display: none;"> We investigate the potential of a restricted Boltzmann Machine (RBM) for discriminative representation learning. By imposing the class information preservation constraints on the hidden layer of the RBM, we propose a Signed Laplacian Restricted Boltzmann Machine (SLRBM) for supervised discriminative representation learning. The model utilizes the label information and preserves the global data locality of data points simultaneously. Experimental results on the benchmark data set show the effectiveness of our method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1808.09389v1-abstract-full').style.display = 'none'; document.getElementById('1808.09389v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 August, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2018. </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 appear in iTWIST'18</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1804.02745">arXiv:1804.02745</a> <span> [<a href="https://arxiv.org/pdf/1804.02745">pdf</a>, <a href="https://arxiv.org/format/1804.02745">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"> Direct Estimation of Pharmacokinetic Parameters from DCE-MRI using Deep CNN with Forward Physical Model Loss </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ulas%2C+C">Cagdas Ulas</a>, <a href="/search/cs?searchtype=author&query=Tetteh%2C+G">Giles Tetteh</a>, <a href="/search/cs?searchtype=author&query=Thrippleton%2C+M+J">Michael J. Thrippleton</a>, <a href="/search/cs?searchtype=author&query=Armitage%2C+P+A">Paul A. Armitage</a>, <a href="/search/cs?searchtype=author&query=Makin%2C+S+D">Stephen D. Makin</a>, <a href="/search/cs?searchtype=author&query=Wardlaw%2C+J+M">Joanna M. Wardlaw</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Menze%2C+B+H">Bjoern H. Menze</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="1804.02745v2-abstract-short" style="display: inline;"> Dynamic contrast-enhanced (DCE) MRI is an evolving imaging technique that provides a quantitative measure of pharmacokinetic (PK) parameters in body tissues, in which series of T1-weighted images are collected following the administration of a paramagnetic contrast agent. Unfortunately, in many applications, conventional clinical DCE-MRI suffers from low spatiotemporal resolution and insufficient… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.02745v2-abstract-full').style.display = 'inline'; document.getElementById('1804.02745v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1804.02745v2-abstract-full" style="display: none;"> Dynamic contrast-enhanced (DCE) MRI is an evolving imaging technique that provides a quantitative measure of pharmacokinetic (PK) parameters in body tissues, in which series of T1-weighted images are collected following the administration of a paramagnetic contrast agent. Unfortunately, in many applications, conventional clinical DCE-MRI suffers from low spatiotemporal resolution and insufficient volume coverage. In this paper, we propose a novel deep learning based approach to directly estimate the PK parameters from undersampled DCE-MRI data. Specifically, we design a custom loss function where we incorporate a forward physical model that relates the PK parameters to corrupted image-time series obtained due to subsampling in k-space. This allows the network to directly exploit the knowledge of true contrast agent kinetics in the training phase, and hence provide more accurate restoration of PK parameters. Experiments on clinical brain DCE datasets demonstrate the efficacy of our approach in terms of fidelity of PK parameter reconstruction and significantly faster parameter inference compared to a model-based iterative reconstruction method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1804.02745v2-abstract-full').style.display = 'none'; document.getElementById('1804.02745v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2018. </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 MICCAI 2018. 9 pages, 6 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1712.04893">arXiv:1712.04893</a> <span> [<a href="https://arxiv.org/pdf/1712.04893">pdf</a>, <a href="https://arxiv.org/format/1712.04893">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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/JSTSP.2018.2850754">10.1109/JSTSP.2018.2850754 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Performance Analysis of Approximate Message Passing for Distributed Compressed Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hannak%2C+G">Gabor Hannak</a>, <a href="/search/cs?searchtype=author&query=Perelli%2C+A">Alessandro Perelli</a>, <a href="/search/cs?searchtype=author&query=Goertz%2C+N">Norbert Goertz</a>, <a href="/search/cs?searchtype=author&query=Matz%2C+G">Gerald Matz</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1712.04893v2-abstract-short" style="display: inline;"> Bayesian approximate message passing (BAMP) is an efficient method in compressed sensing that is nearly optimal in the minimum mean squared error (MMSE) sense. Bayesian approximate message passing (BAMP) performs joint recovery of multiple vectors with identical support and accounts for correlations in the signal of interest and in the noise. In this paper, we show how to reduce the complexity of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.04893v2-abstract-full').style.display = 'inline'; document.getElementById('1712.04893v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1712.04893v2-abstract-full" style="display: none;"> Bayesian approximate message passing (BAMP) is an efficient method in compressed sensing that is nearly optimal in the minimum mean squared error (MMSE) sense. Bayesian approximate message passing (BAMP) performs joint recovery of multiple vectors with identical support and accounts for correlations in the signal of interest and in the noise. In this paper, we show how to reduce the complexity of vector BAMP via a simple joint decorrelation diagonalization) transform of the signal and noise vectors, which also facilitates the subsequent performance analysis. We prove that BAMP and the corresponding state evolution (SE) are equivariant with respect to the joint decorrelation transform and preserve diagonality of the residual noise covariance for the Bernoulli-Gauss (BG) prior. We use these results to analyze the dynamics and the mean squared error (MSE) performance of BAMP via the replica method, and thereby understand the impact of signal correlation and number of jointly sparse signals. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.04893v2-abstract-full').style.display = 'none'; document.getElementById('1712.04893v2-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 August, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 December, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2017. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1706.00092">arXiv:1706.00092</a> <span> [<a href="https://arxiv.org/pdf/1706.00092">pdf</a>, <a href="https://arxiv.org/format/1706.00092">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Inexact Gradient Projection and Fast Data Driven Compressed Sensing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Golbabaee%2C+M">Mohammad Golbabaee</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1706.00092v1-abstract-short" style="display: inline;"> We study convergence of the iterative projected gradient (IPG) algorithm for arbitrary (possibly nonconvex) sets and when both the gradient and projection oracles are computed approximately. We consider different notions of approximation of which we show that the Progressive Fixed Precision (PFP) and the $(1+蔚)$-optimal oracles can achieve the same accuracy as for the exact IPG algorithm. We show… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1706.00092v1-abstract-full').style.display = 'inline'; document.getElementById('1706.00092v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1706.00092v1-abstract-full" style="display: none;"> We study convergence of the iterative projected gradient (IPG) algorithm for arbitrary (possibly nonconvex) sets and when both the gradient and projection oracles are computed approximately. We consider different notions of approximation of which we show that the Progressive Fixed Precision (PFP) and the $(1+蔚)$-optimal oracles can achieve the same accuracy as for the exact IPG algorithm. We show that the former scheme is also able to maintain the (linear) rate of convergence of the exact algorithm, under the same embedding assumption. In contrast, the $(1+蔚)$-approximate oracle requires a stronger embedding condition, moderate compression ratios and it typically slows down the convergence. We apply our results to accelerate solving a class of data driven compressed sensing problems, where we replace iterative exhaustive searches over large datasets by fast approximate nearest neighbour search strategies based on the cover tree data structure. For datasets with low intrinsic dimensions our proposed algorithm achieves a complexity logarithmic in terms of the dataset population as opposed to the linear complexity of a brute force search. By running several numerical experiments we conclude similar observations as predicted by our theoretical analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1706.00092v1-abstract-full').style.display = 'none'; document.getElementById('1706.00092v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 May, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2017. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1609.04661">arXiv:1609.04661</a> <span> [<a href="https://arxiv.org/pdf/1609.04661">pdf</a>, <a href="https://arxiv.org/format/1609.04661">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Physics">physics.comp-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1137/19M1310013">10.1137/19M1310013 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Compressive Computed Tomography Reconstruction through Denoising Approximate Message Passing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Perelli%2C+A">Alessandro Perelli</a>, <a href="/search/cs?searchtype=author&query=Lexa%2C+M">Michael Lexa</a>, <a href="/search/cs?searchtype=author&query=Can%2C+A">Ali Can</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1609.04661v3-abstract-short" style="display: inline;"> X-ray Computed Tomography (CT) reconstruction from a sparse number of views is a useful way to reduce either the radiation dose or the acquisition time, for example in fixed-gantry CT systems, however this results in an ill-posed inverse problem whose solution is typically computationally demanding. Approximate Message Passing (AMP) techniques represent the state of the art for solving under-sampl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1609.04661v3-abstract-full').style.display = 'inline'; document.getElementById('1609.04661v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1609.04661v3-abstract-full" style="display: none;"> X-ray Computed Tomography (CT) reconstruction from a sparse number of views is a useful way to reduce either the radiation dose or the acquisition time, for example in fixed-gantry CT systems, however this results in an ill-posed inverse problem whose solution is typically computationally demanding. Approximate Message Passing (AMP) techniques represent the state of the art for solving under-sampling Compressed Sensing problems with random linear measurements but there are still not clear solutions on how AMP should be modified and how it performs with real world problems. This paper investigates the question of whether we can employ an AMP framework for real sparse view CT imaging? The proposed algorithm for approximate inference in tomographic reconstruction incorporates a number of advances from within the AMP community, resulting in the Denoising Generalized Approximate Message Passing CT algorithm (D-GAMP-CT). Specifically, this exploits the use of sophisticated image denoisers to regularize the reconstruction. While in order to reduce the probability of divergence the (Radon) system and Poisson non-linear noise model are treated separately, exploiting the existence of efficient preconditioners for the former and the generalized noise modelling in GAMP for the latter. Experiments with simulated and real CT baggage scans confirm that the performance of the proposed algorithm outperforms statistical CT optimization solvers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1609.04661v3-abstract-full').style.display = 'none'; document.getElementById('1609.04661v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 September, 2016; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2016. </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">38 pages, 16 figures, to be published in SIAM Journal on Imaging Sciences</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> SIAM Journal on Imaging Sciences, vol. 13, n. 4, pp. 1860-1897, 2020 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1409.0440">arXiv:1409.0440</a> <span> [<a href="https://arxiv.org/pdf/1409.0440">pdf</a>, <a href="https://arxiv.org/ps/1409.0440">ps</a>, <a href="https://arxiv.org/format/1409.0440">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TSP.2015.2408569">10.1109/TSP.2015.2408569 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Near optimal compressed sensing without priors: Parametric SURE Approximate Message Passing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+C">Chunli Guo</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1409.0440v1-abstract-short" style="display: inline;"> Both theoretical analysis and empirical evidence confirm that the approximate message passing (AMP) algorithm can be interpreted as recursively solving a signal denoising problem: at each AMP iteration, one observes a Gaussian noise perturbed original signal. Retrieving the signal amounts to a successive noise cancellation until the noise variance decreases to a satisfactory level. In this paper w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1409.0440v1-abstract-full').style.display = 'inline'; document.getElementById('1409.0440v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1409.0440v1-abstract-full" style="display: none;"> Both theoretical analysis and empirical evidence confirm that the approximate message passing (AMP) algorithm can be interpreted as recursively solving a signal denoising problem: at each AMP iteration, one observes a Gaussian noise perturbed original signal. Retrieving the signal amounts to a successive noise cancellation until the noise variance decreases to a satisfactory level. In this paper we incorporate the Stein's unbiased risk estimate (SURE) based parametric denoiser with the AMP framework and propose the novel parametric SURE-AMP algorithm. At each parametric SURE-AMP iteration, the denoiser is adaptively optimized within the parametric class by minimizing SURE, which depends purely on the noisy observation. In this manner, the parametric SURE-AMP is guaranteed with the best-in-class recovery and convergence rate. If the parameter family includes the families of the mimimum mean squared error (MMSE) estimators, we are able to achieve the Bayesian optimal AMP performance without knowing the signal prior. In the paper, we resort to the linear parameterization of the SURE based denoiser and propose three different kernel families as the base functions. Numerical simulations with the Bernoulli-Gaussian, $k$-dense and Student's-t signals demonstrate that the parametric SURE-AMP does not only achieve the state-of-the-art recovery but also runs more than 20 times faster than the EM-GM-GAMP algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1409.0440v1-abstract-full').style.display = 'none'; document.getElementById('1409.0440v1-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 August, 2014; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2014. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Part of the work will be presented at the European Signal Processing Conference, Lisbon, Portugal, September 2014</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1311.6239">arXiv:1311.6239</a> <span> [<a href="https://arxiv.org/pdf/1311.6239">pdf</a>, <a href="https://arxiv.org/format/1311.6239">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TIT.2014.2364403">10.1109/TIT.2014.2364403 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Fundamental performance limits for ideal decoders in high-dimensional linear inverse problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bourrier%2C+A">Anthony Bourrier</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Peleg%2C+T">Tomer Peleg</a>, <a href="/search/cs?searchtype=author&query=P%C3%A9rez%2C+P">Patrick P茅rez</a>, <a href="/search/cs?searchtype=author&query=Gribonval%2C+R">R茅mi Gribonval</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="1311.6239v2-abstract-short" style="display: inline;"> This paper focuses on characterizing the fundamental performance limits that can be expected from an ideal decoder given a general model, ie, a general subset of "simple" vectors of interest. First, we extend the so-called notion of instance optimality of a decoder to settings where one only wishes to reconstruct some part of the original high dimensional vector from a low-dimensional observation.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1311.6239v2-abstract-full').style.display = 'inline'; document.getElementById('1311.6239v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1311.6239v2-abstract-full" style="display: none;"> This paper focuses on characterizing the fundamental performance limits that can be expected from an ideal decoder given a general model, ie, a general subset of "simple" vectors of interest. First, we extend the so-called notion of instance optimality of a decoder to settings where one only wishes to reconstruct some part of the original high dimensional vector from a low-dimensional observation. This covers practical settings such as medical imaging of a region of interest, or audio source separation when one is only interested in estimating the contribution of a specific instrument to a musical recording. We define instance optimality relatively to a model much beyond the traditional framework of sparse recovery, and characterize the existence of an instance optimal decoder in terms of joint properties of the model and the considered linear operator. Noiseless and noise-robust settings are both considered. We show somewhat surprisingly that the existence of noise-aware instance optimal decoders for all noise levels implies the existence of a noise-blind decoder. A consequence of our results is that for models that are rich enough to contain an orthonormal basis, the existence of an L2/L2 instance optimal decoder is only possible when the linear operator is not substantially dimension-reducing. This covers well-known cases (sparse vectors, low-rank matrices) as well as a number of seemingly new situations (structured sparsity and sparse inverse covariance matrices for instance). We exhibit an operator-dependent norm which, under a model-specific generalization of the Restricted Isometry Property (RIP), always yields a feasible instance optimality property. This norm can be upper bounded by an atomic norm relative to the considered model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1311.6239v2-abstract-full').style.display = 'none'; document.getElementById('1311.6239v2-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 October, 2014; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 November, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2013. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in IEEE Transactions on Information Theory</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Information Theory, 60(12):7928-7946, December 2014 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1303.5492">arXiv:1303.5492</a> <span> [<a href="https://arxiv.org/pdf/1303.5492">pdf</a>, <a href="https://arxiv.org/ps/1303.5492">ps</a>, <a href="https://arxiv.org/format/1303.5492">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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/10.1109/TSP.2013.2286775">10.1109/TSP.2013.2286775 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Sample Distortion for Compressed Imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+C">Chunli Guo</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1303.5492v2-abstract-short" style="display: inline;"> We propose the notion of a sample distortion (SD) function for independent and identically distributed (i.i.d) compressive distributions to fundamentally quantify the achievable reconstruction performance of compressed sensing for certain encoder-decoder pairs at a given sampling ratio. Two lower bounds on the achievable performance and the intrinsic convexity property is derived. A zeroing proced… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1303.5492v2-abstract-full').style.display = 'inline'; document.getElementById('1303.5492v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1303.5492v2-abstract-full" style="display: none;"> We propose the notion of a sample distortion (SD) function for independent and identically distributed (i.i.d) compressive distributions to fundamentally quantify the achievable reconstruction performance of compressed sensing for certain encoder-decoder pairs at a given sampling ratio. Two lower bounds on the achievable performance and the intrinsic convexity property is derived. A zeroing procedure is then introduced to improve non convex SD functions. The SD framework is then applied to analyse compressed imaging with a multi-resolution statistical image model using both the generalized Gaussian distribution and the two-state Gaussian mixture distribution. We subsequently focus on the Gaussian encoder-Bayesian optimal approximate message passing (AMP) decoder pair, whose theoretical SD function is provided by the rigorous analysis of the AMP algorithm. Given the image statistics, analytic bandwise sample allocation for bandwise independent model is derived as a reverse water-filling scheme. Som and Schniter's turbo message passing approach is further deployed to integrate the bandwise sampling with the exploitation of the hidden Markov tree structure of wavelet coefficients. Natural image simulations confirm that with oracle image statistics, the SD function associated with the optimized sample allocation can accurately predict the possible compressed sensing gains. Finally, a general sample allocation profile based on average image statistics not only illustrates preferable performance but also makes the scheme practical. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1303.5492v2-abstract-full').style.display = 'none'; document.getElementById('1303.5492v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 July, 2013; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 March, 2013; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2013. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 10 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/1212.2834">arXiv:1212.2834</a> <span> [<a href="https://arxiv.org/pdf/1212.2834">pdf</a>, <a href="https://arxiv.org/format/1212.2834">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="Optimization and Control">math.OC</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"> Dictionary Subselection Using an Overcomplete Joint Sparsity Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yaghoobi%2C+M">Mehrdad Yaghoobi</a>, <a href="/search/cs?searchtype=author&query=Daudet%2C+L">Laurent Daudet</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Michael E. Davies</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1212.2834v2-abstract-short" style="display: inline;"> Many natural signals exhibit a sparse representation, whenever a suitable describing model is given. Here, a linear generative model is considered, where many sparsity-based signal processing techniques rely on such a simplified model. As this model is often unknown for many classes of the signals, we need to select such a model based on the domain knowledge or using some exemplar signals. This pa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1212.2834v2-abstract-full').style.display = 'inline'; document.getElementById('1212.2834v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1212.2834v2-abstract-full" style="display: none;"> Many natural signals exhibit a sparse representation, whenever a suitable describing model is given. Here, a linear generative model is considered, where many sparsity-based signal processing techniques rely on such a simplified model. As this model is often unknown for many classes of the signals, we need to select such a model based on the domain knowledge or using some exemplar signals. This paper presents a new exemplar based approach for the linear model (called the dictionary) selection, for such sparse inverse problems. The problem of dictionary selection, which has also been called the dictionary learning in this setting, is first reformulated as a joint sparsity model. The joint sparsity model here differs from the standard joint sparsity model as it considers an overcompleteness in the representation of each signal, within the range of selected subspaces. The new dictionary selection paradigm is examined with some synthetic and realistic simulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1212.2834v2-abstract-full').style.display = 'none'; document.getElementById('1212.2834v2-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 June, 2013; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 December, 2012; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2012. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">the title previously was "Optimal Dictionary Selection Using an Overcomplete Joint Sparsity Model"</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1205.4133">arXiv:1205.4133</a> <span> [<a href="https://arxiv.org/pdf/1205.4133">pdf</a>, <a href="https://arxiv.org/ps/1205.4133">ps</a>, <a href="https://arxiv.org/format/1205.4133">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</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/TSP.2013.2250968">10.1109/TSP.2013.2250968 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Constrained Overcomplete Analysis Operator Learning for Cosparse Signal Modelling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yaghoobi%2C+M">Mehrdad Yaghoobi</a>, <a href="/search/cs?searchtype=author&query=Nam%2C+S">Sangnam Nam</a>, <a href="/search/cs?searchtype=author&query=Gribonval%2C+R">Remi Gribonval</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1205.4133v2-abstract-short" style="display: inline;"> We consider the problem of learning a low-dimensional signal model from a collection of training samples. The mainstream approach would be to learn an overcomplete dictionary to provide good approximations of the training samples using sparse synthesis coefficients. This famous sparse model has a less well known counterpart, in analysis form, called the cosparse analysis model. In this new model,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1205.4133v2-abstract-full').style.display = 'inline'; document.getElementById('1205.4133v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1205.4133v2-abstract-full" style="display: none;"> We consider the problem of learning a low-dimensional signal model from a collection of training samples. The mainstream approach would be to learn an overcomplete dictionary to provide good approximations of the training samples using sparse synthesis coefficients. This famous sparse model has a less well known counterpart, in analysis form, called the cosparse analysis model. In this new model, signals are characterised by their parsimony in a transformed domain using an overcomplete (linear) analysis operator. We propose to learn an analysis operator from a training corpus using a constrained optimisation framework based on L1 optimisation. The reason for introducing a constraint in the optimisation framework is to exclude trivial solutions. Although there is no final answer here for which constraint is the most relevant constraint, we investigate some conventional constraints in the model adaptation field and use the uniformly normalised tight frame (UNTF) for this purpose. We then derive a practical learning algorithm, based on projected subgradients and Douglas-Rachford splitting technique, and demonstrate its ability to robustly recover a ground truth analysis operator, when provided with a clean training set, of sufficient size. We also find an analysis operator for images, using some noisy cosparse signals, which is indeed a more realistic experiment. As the derived optimisation problem is not a convex program, we often find a local minimum using such variational methods. Some local optimality conditions are derived for two different settings, providing preliminary theoretical support for the well-posedness of the learning problem under appropriate conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1205.4133v2-abstract-full').style.display = 'none'; document.getElementById('1205.4133v2-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, 2013; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 May, 2012; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2012. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">29 pages, 13 figures, accepted to be published in TSP</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1110.2722">arXiv:1110.2722</a> <span> [<a href="https://arxiv.org/pdf/1110.2722">pdf</a>, <a href="https://arxiv.org/ps/1110.2722">ps</a>, <a href="https://arxiv.org/format/1110.2722">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Compressive and Noncompressive Power Spectral Density Estimation from Periodic Nonuniform Samples </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lexa%2C+M+A">Michael A. Lexa</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Thompson%2C+J+S">John S. Thompson</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="1110.2722v2-abstract-short" style="display: inline;"> This paper presents a novel power spectral density estimation technique for band-limited, wide-sense stationary signals from sub-Nyquist sampled data. The technique employs multi-coset sampling and incorporates the advantages of compressed sensing (CS) when the power spectrum is sparse, but applies to sparse and nonsparse power spectra alike. The estimates are consistent piecewise constant approxi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1110.2722v2-abstract-full').style.display = 'inline'; document.getElementById('1110.2722v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1110.2722v2-abstract-full" style="display: none;"> This paper presents a novel power spectral density estimation technique for band-limited, wide-sense stationary signals from sub-Nyquist sampled data. The technique employs multi-coset sampling and incorporates the advantages of compressed sensing (CS) when the power spectrum is sparse, but applies to sparse and nonsparse power spectra alike. The estimates are consistent piecewise constant approximations whose resolutions (width of the piecewise constant segments) are controlled by the periodicity of the multi-coset sampling. We show that compressive estimates exhibit better tradeoffs among the estimator's resolution, system complexity, and average sampling rate compared to their noncompressive counterparts. For suitable sampling patterns, noncompressive estimates are obtained as least squares solutions. Because of the non-negativity of power spectra, compressive estimates can be computed by seeking non-negative least squares solutions (provided appropriate sampling patterns exist) instead of using standard CS recovery algorithms. This flexibility suggests a reduction in computational overhead for systems estimating both sparse and nonsparse power spectra because one algorithm can be used to compute both compressive and noncompressive estimates. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1110.2722v2-abstract-full').style.display = 'none'; document.getElementById('1110.2722v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 May, 2012; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 October, 2011; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2011. </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">26 pages, single spaced, 9 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1106.4987">arXiv:1106.4987</a> <span> [<a href="https://arxiv.org/pdf/1106.4987">pdf</a>, <a href="https://arxiv.org/ps/1106.4987">ps</a>, <a href="https://arxiv.org/format/1106.4987">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</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/10.1016/j.acha.2012.03.006">10.1016/j.acha.2012.03.006 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> The Cosparse Analysis Model and Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nam%2C+S">Sangnam Nam</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Elad%2C+M">Michael Elad</a>, <a href="/search/cs?searchtype=author&query=Gribonval%2C+R">R茅mi Gribonval</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="1106.4987v1-abstract-short" style="display: inline;"> After a decade of extensive study of the sparse representation synthesis model, we can safely say that this is a mature and stable field, with clear theoretical foundations, and appealing applications. Alongside this approach, there is an analysis counterpart model, which, despite its similarity to the synthesis alternative, is markedly different. Surprisingly, the analysis model did not get a sim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1106.4987v1-abstract-full').style.display = 'inline'; document.getElementById('1106.4987v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1106.4987v1-abstract-full" style="display: none;"> After a decade of extensive study of the sparse representation synthesis model, we can safely say that this is a mature and stable field, with clear theoretical foundations, and appealing applications. Alongside this approach, there is an analysis counterpart model, which, despite its similarity to the synthesis alternative, is markedly different. Surprisingly, the analysis model did not get a similar attention, and its understanding today is shallow and partial. In this paper we take a closer look at the analysis approach, better define it as a generative model for signals, and contrast it with the synthesis one. This work proposes effective pursuit methods that aim to solve inverse problems regularized with the analysis-model prior, accompanied by a preliminary theoretical study of their performance. We demonstrate the effectiveness of the analysis model in several experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1106.4987v1-abstract-full').style.display = 'none'; document.getElementById('1106.4987v1-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 June, 2011; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2011. </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 (2011)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1102.1249">arXiv:1102.1249</a> <span> [<a href="https://arxiv.org/pdf/1102.1249">pdf</a>, <a href="https://arxiv.org/ps/1102.1249">ps</a>, <a href="https://arxiv.org/format/1102.1249">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</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/10.1109/TIT.2012.2197174">10.1109/TIT.2012.2197174 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Compressible Distributions for High-dimensional Statistics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gribonval%2C+R">R茅mi Gribonval</a>, <a href="/search/cs?searchtype=author&query=Cevher%2C+V">Volkan Cevher</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</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="1102.1249v3-abstract-short" style="display: inline;"> We develop a principled way of identifying probability distributions whose independent and identically distributed (iid) realizations are compressible, i.e., can be well-approximated as sparse. We focus on Gaussian random underdetermined linear regression (GULR) problems, where compressibility is known to ensure the success of estimators exploiting sparse regularization. We prove that many distrib… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1102.1249v3-abstract-full').style.display = 'inline'; document.getElementById('1102.1249v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1102.1249v3-abstract-full" style="display: none;"> We develop a principled way of identifying probability distributions whose independent and identically distributed (iid) realizations are compressible, i.e., can be well-approximated as sparse. We focus on Gaussian random underdetermined linear regression (GULR) problems, where compressibility is known to ensure the success of estimators exploiting sparse regularization. We prove that many distributions revolving around maximum a posteriori (MAP) interpretation of sparse regularized estimators are in fact incompressible, in the limit of large problem sizes. A highlight is the Laplace distribution and $\ell^{1}$ regularized estimators such as the Lasso and Basis Pursuit denoising. To establish this result, we identify non-trivial undersampling regions in GULR where the simple least squares solution almost surely outperforms an oracle sparse solution, when the data is generated from the Laplace distribution. We provide simple rules of thumb to characterize classes of compressible (respectively incompressible) distributions based on their second and fourth moments. Generalized Gaussians and generalized Pareto distributions serve as running examples for concreteness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1102.1249v3-abstract-full').style.display = 'none'; document.getElementById('1102.1249v3-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 April, 2012; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 February, 2011; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2011. </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">Was previously entitled "Compressible priors for high-dimensional statistics"; IEEE Transactions on Information Theory (2012)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1101.4100">arXiv:1101.4100</a> <span> [<a href="https://arxiv.org/pdf/1101.4100">pdf</a>, <a href="https://arxiv.org/ps/1101.4100">ps</a>, <a href="https://arxiv.org/format/1101.4100">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TSP.2011.2169408">10.1109/TSP.2011.2169408 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Reconciling Compressive Sampling Systems for Spectrally-sparse Continuous-time Signals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lexa%2C+M+A">Michael A. Lexa</a>, <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Thompson%2C+J+S">John S. Thompson</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="1101.4100v3-abstract-short" style="display: inline;"> The Random Demodulator (RD) and the Modulated Wideband Converter (MWC) are two recently proposed compressed sensing (CS) techniques for the acquisition of continuous-time spectrally-sparse signals. They extend the standard CS paradigm from sampling discrete, finite dimensional signals to sampling continuous and possibly infinite dimensional ones, and thus establish the ability to capture these sig… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1101.4100v3-abstract-full').style.display = 'inline'; document.getElementById('1101.4100v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1101.4100v3-abstract-full" style="display: none;"> The Random Demodulator (RD) and the Modulated Wideband Converter (MWC) are two recently proposed compressed sensing (CS) techniques for the acquisition of continuous-time spectrally-sparse signals. They extend the standard CS paradigm from sampling discrete, finite dimensional signals to sampling continuous and possibly infinite dimensional ones, and thus establish the ability to capture these signals at sub-Nyquist sampling rates. The RD and the MWC have remarkably similar structures (similar block diagrams), but their reconstruction algorithms and signal models strongly differ. To date, few results exist that compare these systems, and owing to the potential impacts they could have on spectral estimation in applications like electromagnetic scanning and cognitive radio, we more fully investigate their relationship in this paper. We show that the RD and the MWC are both based on the general concept of random filtering, but employ significantly different sampling functions. We also investigate system sensitivities (or robustness) to sparse signal model assumptions. Lastly, we show that "block convolution" is a fundamental aspect of the MWC, allowing it to successfully sample and reconstruct block-sparse (multiband) signals. Based on this concept, we propose a new acquisition system for continuous-time signals whose amplitudes are block sparse. The paper includes detailed time and frequency domain analyses of the RD and the MWC that differ, sometimes substantially, from published results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1101.4100v3-abstract-full').style.display = 'none'; document.getElementById('1101.4100v3-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 October, 2011; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 January, 2011; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2011. </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">Corrected typos, updated Section 4.3, 30 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/1004.4529">arXiv:1004.4529</a> <span> [<a href="https://arxiv.org/pdf/1004.4529">pdf</a>, <a href="https://arxiv.org/ps/1004.4529">ps</a>, <a href="https://arxiv.org/format/1004.4529">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Rank Awareness in Joint Sparse Recovery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Davies%2C+M+E">Mike E. Davies</a>, <a href="/search/cs?searchtype=author&query=Eldar%2C+Y+C">Yonina C. Eldar</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="1004.4529v1-abstract-short" style="display: inline;"> In this paper we revisit the sparse multiple measurement vector (MMV) problem where the aim is to recover a set of jointly sparse multichannel vectors from incomplete measurements. This problem has received increasing interest as an extension of the single channel sparse recovery problem which lies at the heart of the emerging field of compressed sensing. However the sparse approximation problem h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1004.4529v1-abstract-full').style.display = 'inline'; document.getElementById('1004.4529v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1004.4529v1-abstract-full" style="display: none;"> In this paper we revisit the sparse multiple measurement vector (MMV) problem where the aim is to recover a set of jointly sparse multichannel vectors from incomplete measurements. This problem has received increasing interest as an extension of the single channel sparse recovery problem which lies at the heart of the emerging field of compressed sensing. However the sparse approximation problem has origins which include links to the field of array signal processing where we find the inspiration for a new family of MMV algorithms based on the MUSIC algorithm. We highlight the role of the rank of the coefficient matrix X in determining the difficulty of the recovery problem. We derive the necessary and sufficient conditions for the uniqueness of the sparse MMV solution, which indicates that the larger the rank of X the less sparse X needs to be to ensure uniqueness. We also show that the larger the rank of X the less the computational effort required to solve the MMV problem through a combinatorial search. In the second part of the paper we consider practical suboptimal algorithms for solving the sparse MMV problem. We examine the rank awareness of popular algorithms such as SOMP and mixed norm minimization techniques and show them to be rank blind in terms of worst case analysis. We then consider a family of greedy algorithms that are rank aware. The simplest such algorithm is a discrete version of MUSIC and is guaranteed to recover the sparse vectors in the full rank MMV case under mild conditions. We extend this idea to develop a rank aware pursuit algorithm that naturally reduces to Order Recursive Matching Pursuit (ORMP) in the single measurement case and also provides guaranteed recovery in the full rank multi-measurement case. Numerical simulations demonstrate that the rank aware algorithms are significantly better than existing algorithms in dealing with multiple measurements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1004.4529v1-abstract-full').style.display = 'none'; document.getElementById('1004.4529v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 April, 2010; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2010. </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">23 pages, 2 figures</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Davies%2C+M+E&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Davies%2C+M+E&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Davies%2C+M+E&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository