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 65 results for author: <span class="mathjax">Pun, C</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Pun%2C+C">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Pun, C"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Pun%2C+C&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Pun, C"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <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=Pun%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Pun%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Pun%2C+C&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/2411.09268">arXiv:2411.09268</a> <span> [<a href="https://arxiv.org/pdf/2411.09268">pdf</a>, <a href="https://arxiv.org/format/2411.09268">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"> LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feng%2C+G">Guanwen Feng</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+Z">Zhihao Qian</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yunan Li</a>, <a href="/search/cs?searchtype=author&query=Jin%2C+S">Siyu Jin</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+Q">Qiguang Miao</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2411.09268v1-abstract-short" style="display: inline;"> While existing one-shot talking head generation models have achieved progress in coarse-grained emotion editing, there is still a lack of fine-grained emotion editing models with high interpretability. We argue that for an approach to be considered fine-grained, it needs to provide clear definitions and sufficiently detailed differentiation. We present LES-Talker, a novel one-shot talking head gen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09268v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09268v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09268v1-abstract-full" style="display: none;"> While existing one-shot talking head generation models have achieved progress in coarse-grained emotion editing, there is still a lack of fine-grained emotion editing models with high interpretability. We argue that for an approach to be considered fine-grained, it needs to provide clear definitions and sufficiently detailed differentiation. We present LES-Talker, a novel one-shot talking head generation model with high interpretability, to achieve fine-grained emotion editing across emotion types, emotion levels, and facial units. We propose a Linear Emotion Space (LES) definition based on Facial Action Units to characterize emotion transformations as vector transformations. We design the Cross-Dimension Attention Net (CDAN) to deeply mine the correlation between LES representation and 3D model representation. Through mining multiple relationships across different feature and structure dimensions, we enable LES representation to guide the controllable deformation of 3D model. In order to adapt the multimodal data with deviations to the LES and enhance visual quality, we utilize specialized network design and training strategies. Experiments show that our method provides high visual quality along with multilevel and interpretable fine-grained emotion editing, outperforming mainstream methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09268v1-abstract-full').style.display = 'none'; document.getElementById('2411.09268v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.05276">arXiv:2411.05276</a> <span> [<a href="https://arxiv.org/pdf/2411.05276">pdf</a>, <a href="https://arxiv.org/format/2411.05276">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Regmi%2C+S">Sajal Regmi</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C+P">Chetan Phakami Pun</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="2411.05276v1-abstract-short" style="display: inline;"> Large Language Models (LLMs), such as GPT (Radford et al., 2019), have significantly advanced artificial intelligence by enabling sophisticated natural language understanding and generation. However, the high computational and financial costs associated with frequent API calls to these models present a substantial bottleneck, especially for applications like customer service chatbots that handle r… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05276v1-abstract-full').style.display = 'inline'; document.getElementById('2411.05276v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.05276v1-abstract-full" style="display: none;"> Large Language Models (LLMs), such as GPT (Radford et al., 2019), have significantly advanced artificial intelligence by enabling sophisticated natural language understanding and generation. However, the high computational and financial costs associated with frequent API calls to these models present a substantial bottleneck, especially for applications like customer service chatbots that handle repetitive queries. In this paper, we introduce GPT Semantic Cache, a method that leverages semantic caching of query embeddings in in-memory storage (Redis). By storing embeddings of user queries, our approach efficiently identifies semantically similar questions, allowing for the retrieval of pre-generated responses without redundant API calls to the LLM. This technique reduces operational costs and improves response times, enhancing the efficiency of LLM-powered applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.05276v1-abstract-full').style.display = 'none'; document.getElementById('2411.05276v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18551">arXiv:2410.18551</a> <span> [<a href="https://arxiv.org/pdf/2410.18551">pdf</a>, <a href="https://arxiv.org/format/2410.18551">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> IMAN: An Adaptive Network for Robust NPC Mortality Prediction with Missing Modalities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huo%2C+Y">Yejing Huo</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Guoheng Huang</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+L">Lianglun Cheng</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Jianbin He</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xiaochen Yuan</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+G">Guo Zhong</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2410.18551v1-abstract-short" style="display: inline;"> Accurate prediction of mortality in nasopharyngeal carcinoma (NPC), a complex malignancy particularly challenging in advanced stages, is crucial for optimizing treatment strategies and improving patient outcomes. However, this predictive process is often compromised by the high-dimensional and heterogeneous nature of NPC-related data, coupled with the pervasive issue of incomplete multi-modal data… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18551v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18551v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18551v1-abstract-full" style="display: none;"> Accurate prediction of mortality in nasopharyngeal carcinoma (NPC), a complex malignancy particularly challenging in advanced stages, is crucial for optimizing treatment strategies and improving patient outcomes. However, this predictive process is often compromised by the high-dimensional and heterogeneous nature of NPC-related data, coupled with the pervasive issue of incomplete multi-modal data, manifesting as missing radiological images or incomplete diagnostic reports. Traditional machine learning approaches suffer significant performance degradation when faced with such incomplete data, as they fail to effectively handle the high-dimensionality and intricate correlations across modalities. Even advanced multi-modal learning techniques like Transformers struggle to maintain robust performance in the presence of missing modalities, as they lack specialized mechanisms to adaptively integrate and align the diverse data types, while also capturing nuanced patterns and contextual relationships within the complex NPC data. To address these problem, we introduce IMAN: an adaptive network for robust NPC mortality prediction with missing modalities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18551v1-abstract-full').style.display = 'none'; document.getElementById('2410.18551v1-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 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">The paper has been accepted by BIBM 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/2410.07695">arXiv:2410.07695</a> <span> [<a href="https://arxiv.org/pdf/2410.07695">pdf</a>, <a href="https://arxiv.org/format/2410.07695">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"> Test-Time Intensity Consistency Adaptation for Shadow Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+L">Leyi Zhu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weihuang Liu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinyi Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zimeng Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhen Wang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2410.07695v2-abstract-short" style="display: inline;"> Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context. Deep learning models often struggle to generalize to real-world images due to the limited size and diversity of training datasets. To address this, we introduce TICA, a novel framework t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07695v2-abstract-full').style.display = 'inline'; document.getElementById('2410.07695v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.07695v2-abstract-full" style="display: none;"> Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context. Deep learning models often struggle to generalize to real-world images due to the limited size and diversity of training datasets. To address this, we introduce TICA, a novel framework that leverages light-intensity information during test-time adaptation to enhance shadow detection accuracy. TICA exploits the inherent inconsistencies in light intensity across shadow regions to guide the model toward a more consistent prediction. A basic encoder-decoder model is initially trained on a labeled dataset for shadow detection. Then, during the testing phase, the network is adjusted for each test sample by enforcing consistent intensity predictions between two augmented input image versions. This consistency training specifically targets both foreground and background intersection regions to identify shadow regions within images accurately for robust adaptation. Extensive evaluations on the ISTD and SBU shadow detection datasets reveal that TICA significantly demonstrates that TICA outperforms existing state-of-the-art methods, achieving superior results in balanced error rate (BER). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.07695v2-abstract-full').style.display = 'none'; document.getElementById('2410.07695v2-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">v1</span> submitted 10 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">15 pages, 5 figures, published to ICONIP 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/2410.04032">arXiv:2410.04032</a> <span> [<a href="https://arxiv.org/pdf/2410.04032">pdf</a>, <a href="https://arxiv.org/format/2410.04032">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"> ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weihuang Liu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+X">Xi Shen</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</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="2410.04032v1-abstract-short" style="display: inline;"> Social media is increasingly plagued by realistic fake images, making it hard to trust content. Previous algorithms to detect these fakes often fail in new, real-world scenarios because they are trained on specific datasets. To address the problem, we introduce ForgeryTTT, the first method leveraging test-time training (TTT) to identify manipulated regions in images. The proposed approach fine-tun… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04032v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04032v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04032v1-abstract-full" style="display: none;"> Social media is increasingly plagued by realistic fake images, making it hard to trust content. Previous algorithms to detect these fakes often fail in new, real-world scenarios because they are trained on specific datasets. To address the problem, we introduce ForgeryTTT, the first method leveraging test-time training (TTT) to identify manipulated regions in images. The proposed approach fine-tunes the model for each individual test sample, improving its performance. ForgeryTTT first employs vision transformers as a shared image encoder to learn both classification and localization tasks simultaneously during the training-time training using a large synthetic dataset. Precisely, the localization head predicts a mask to highlight manipulated areas. Given such a mask, the input tokens can be divided into manipulated and genuine groups, which are then fed into the classification head to distinguish between manipulated and genuine parts. During test-time training, the predicted mask from the localization head is used for the classification head to update the image encoder for better adaptation. Additionally, using the classical dropout strategy in each token group significantly improves performance and efficiency. We test ForgeryTTT on five standard benchmarks. Despite its simplicity, ForgeryTTT achieves a 20.1% improvement in localization accuracy compared to other zero-shot methods and a 4.3% improvement over non-zero-shot techniques. Our code and data will be released upon publication. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04032v1-abstract-full').style.display = 'none'; document.getElementById('2410.04032v1-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 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">Technical Report</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.07793">arXiv:2409.07793</a> <span> [<a href="https://arxiv.org/pdf/2409.07793">pdf</a>, <a href="https://arxiv.org/format/2409.07793">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Lagrange Duality and Compound Multi-Attention Transformer for Semi-Supervised Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+F">Fuchen Zheng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Q">Quanjun Li</a>, <a href="/search/cs?searchtype=author&query=Li%2C+W">Weixuan Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Y">Yihang Dong</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Guoheng Huang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shoujun Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.07793v1-abstract-short" style="display: inline;"> Medical image segmentation, a critical application of semantic segmentation in healthcare, has seen significant advancements through specialized computer vision techniques. While deep learning-based medical image segmentation is essential for assisting in medical diagnosis, the lack of diverse training data causes the long-tail problem. Moreover, most previous hybrid CNN-ViT architectures have lim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07793v1-abstract-full').style.display = 'inline'; document.getElementById('2409.07793v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07793v1-abstract-full" style="display: none;"> Medical image segmentation, a critical application of semantic segmentation in healthcare, has seen significant advancements through specialized computer vision techniques. While deep learning-based medical image segmentation is essential for assisting in medical diagnosis, the lack of diverse training data causes the long-tail problem. Moreover, most previous hybrid CNN-ViT architectures have limited ability to combine various attentions in different layers of the Convolutional Neural Network. To address these issues, we propose a Lagrange Duality Consistency (LDC) Loss, integrated with Boundary-Aware Contrastive Loss, as the overall training objective for semi-supervised learning to mitigate the long-tail problem. Additionally, we introduce CMAformer, a novel network that synergizes the strengths of ResUNet and Transformer. The cross-attention block in CMAformer effectively integrates spatial attention and channel attention for multi-scale feature fusion. Overall, our results indicate that CMAformer, combined with the feature fusion framework and the new consistency loss, demonstrates strong complementarity in semi-supervised learning ensembles. We achieve state-of-the-art results on multiple public medical image datasets. Example code are available at: \url{https://github.com/lzeeorno/Lagrange-Duality-and-CMAformer}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07793v1-abstract-full').style.display = 'none'; document.getElementById('2409.07793v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 4 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.07779">arXiv:2409.07779</a> <span> [<a href="https://arxiv.org/pdf/2409.07779">pdf</a>, <a href="https://arxiv.org/format/2409.07779">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> ASSNet: Adaptive Semantic Segmentation Network for Microtumors and Multi-Organ Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+F">Fuchen Zheng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xinyi Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haolun Li</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+X">Xiaojiao Guo</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Guoheng Huang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shoujun Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.07779v1-abstract-short" style="display: inline;"> Medical image segmentation, a crucial task in computer vision, facilitates the automated delineation of anatomical structures and pathologies, supporting clinicians in diagnosis, treatment planning, and disease monitoring. Notably, transformers employing shifted window-based self-attention have demonstrated exceptional performance. However, their reliance on local window attention limits the fusio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07779v1-abstract-full').style.display = 'inline'; document.getElementById('2409.07779v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07779v1-abstract-full" style="display: none;"> Medical image segmentation, a crucial task in computer vision, facilitates the automated delineation of anatomical structures and pathologies, supporting clinicians in diagnosis, treatment planning, and disease monitoring. Notably, transformers employing shifted window-based self-attention have demonstrated exceptional performance. However, their reliance on local window attention limits the fusion of local and global contextual information, crucial for segmenting microtumors and miniature organs. To address this limitation, we propose the Adaptive Semantic Segmentation Network (ASSNet), a transformer architecture that effectively integrates local and global features for precise medical image segmentation. ASSNet comprises a transformer-based U-shaped encoder-decoder network. The encoder utilizes shifted window self-attention across five resolutions to extract multi-scale features, which are then propagated to the decoder through skip connections. We introduce an augmented multi-layer perceptron within the encoder to explicitly model long-range dependencies during feature extraction. Recognizing the constraints of conventional symmetrical encoder-decoder designs, we propose an Adaptive Feature Fusion (AFF) decoder to complement our encoder. This decoder incorporates three key components: the Long Range Dependencies (LRD) block, the Multi-Scale Feature Fusion (MFF) block, and the Adaptive Semantic Center (ASC) block. These components synergistically facilitate the effective fusion of multi-scale features extracted by the decoder while capturing long-range dependencies and refining object boundaries. Comprehensive experiments on diverse medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, demonstrate that ASSNet achieves state-of-the-art results. Code and models are available at: \url{https://github.com/lzeeorno/ASSNet}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07779v1-abstract-full').style.display = 'none'; document.getElementById('2409.07779v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 4 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.01236">arXiv:2409.01236</a> <span> [<a href="https://arxiv.org/pdf/2409.01236">pdf</a>, <a href="https://arxiv.org/format/2409.01236">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"> Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+K">Kangdao Liu</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tianhao Sun</a>, <a href="/search/cs?searchtype=author&query=Zeng%2C+H">Hao Zeng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yongshan Zhang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Vong%2C+C">Chi-Man Vong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.01236v2-abstract-short" style="display: inline;"> Hyperspectral image (HSI) classification involves assigning unique labels to each pixel to identify various land cover categories. While deep classifiers have achieved high predictive accuracy in this field, they lack the ability to rigorously quantify confidence in their predictions. Quantifying the certainty of model predictions is crucial for the safe usage of predictive models, and this limita… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01236v2-abstract-full').style.display = 'inline'; document.getElementById('2409.01236v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.01236v2-abstract-full" style="display: none;"> Hyperspectral image (HSI) classification involves assigning unique labels to each pixel to identify various land cover categories. While deep classifiers have achieved high predictive accuracy in this field, they lack the ability to rigorously quantify confidence in their predictions. Quantifying the certainty of model predictions is crucial for the safe usage of predictive models, and this limitation restricts their application in critical contexts where the cost of prediction errors is significant. To support the safe deployment of HSI classifiers, we first provide a theoretical proof establishing the validity of the emerging uncertainty quantification technique, conformal prediction, in the context of HSI classification. We then propose a conformal procedure that equips any trained HSI classifier with trustworthy prediction sets, ensuring that these sets include the true labels with a user-specified probability (e.g., 95\%). Building on this foundation, we introduce Spatial-Aware Conformal Prediction (\texttt{SACP}), a conformal prediction framework specifically designed for HSI data. This method integrates essential spatial information inherent in HSIs by aggregating the non-conformity scores of pixels with high spatial correlation, which effectively enhances the efficiency of prediction sets. Both theoretical and empirical results validate the effectiveness of our proposed approach. The source code is available at \url{https://github.com/J4ckLiu/SACP}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.01236v2-abstract-full').style.display = 'none'; document.getElementById('2409.01236v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.00346">arXiv:2409.00346</a> <span> [<a href="https://arxiv.org/pdf/2409.00346">pdf</a>, <a href="https://arxiv.org/format/2409.00346">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"> SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+F">Fuchen Zheng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weihuang Liu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haolun Li</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Y">Yingtie Lei</a>, <a href="/search/cs?searchtype=author&query=He%2C+J">Jiahui He</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+S">Shounjun Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.00346v2-abstract-short" style="display: inline;"> In medical image segmentation, specialized computer vision techniques, notably transformers grounded in attention mechanisms and residual networks employing skip connections, have been instrumental in advancing performance. Nonetheless, previous models often falter when segmenting small, irregularly shaped tumors. To this end, we introduce SMAFormer, an efficient, Transformer-based architecture th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00346v2-abstract-full').style.display = 'inline'; document.getElementById('2409.00346v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00346v2-abstract-full" style="display: none;"> In medical image segmentation, specialized computer vision techniques, notably transformers grounded in attention mechanisms and residual networks employing skip connections, have been instrumental in advancing performance. Nonetheless, previous models often falter when segmenting small, irregularly shaped tumors. To this end, we introduce SMAFormer, an efficient, Transformer-based architecture that fuses multiple attention mechanisms for enhanced segmentation of small tumors and organs. SMAFormer can capture both local and global features for medical image segmentation. The architecture comprises two pivotal components. First, a Synergistic Multi-Attention (SMA) Transformer block is proposed, which has the benefits of Pixel Attention, Channel Attention, and Spatial Attention for feature enrichment. Second, addressing the challenge of information loss incurred during attention mechanism transitions and feature fusion, we design a Feature Fusion Modulator. This module bolsters the integration between the channel and spatial attention by mitigating reshaping-induced information attrition. To evaluate our method, we conduct extensive experiments on various medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, achieving state-of-the-art results. Code and models are available at: \url{https://github.com/CXH-Research/SMAFormer}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00346v2-abstract-full').style.display = 'none'; document.getElementById('2409.00346v2-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE BIBM 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.10653">arXiv:2408.10653</a> <span> [<a href="https://arxiv.org/pdf/2408.10653">pdf</a>, <a href="https://arxiv.org/format/2408.10653">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"> UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lei%2C+Y">Yingtie Lei</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+J">Jia Yu</a>, <a href="/search/cs?searchtype=author&query=Dong%2C+Y">Yihang Dong</a>, <a href="/search/cs?searchtype=author&query=Gong%2C+C">Changwei Gong</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Ziyang Zhou</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.10653v1-abstract-short" style="display: inline;"> Underwater image enhancement (UIE) plays a crucial role in various marine applications, but it remains challenging due to the complex underwater environment. Current learning-based approaches frequently lack explicit incorporation of prior knowledge about the physical processes involved in underwater image formation, resulting in limited optimization despite their impressive enhancement results. T… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10653v1-abstract-full').style.display = 'inline'; document.getElementById('2408.10653v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.10653v1-abstract-full" style="display: none;"> Underwater image enhancement (UIE) plays a crucial role in various marine applications, but it remains challenging due to the complex underwater environment. Current learning-based approaches frequently lack explicit incorporation of prior knowledge about the physical processes involved in underwater image formation, resulting in limited optimization despite their impressive enhancement results. This paper proposes a novel deep unfolding network (DUN) for UIE that integrates color priors and inter-stage feature transformation to improve enhancement performance. The proposed DUN model combines the iterative optimization and reliability of model-based methods with the flexibility and representational power of deep learning, offering a more explainable and stable solution compared to existing learning-based UIE approaches. The proposed model consists of three key components: a Color Prior Guidance Block (CPGB) that establishes a mapping between color channels of degraded and original images, a Nonlinear Activation Gradient Descent Module (NAGDM) that simulates the underwater image degradation process, and an Inter Stage Feature Transformer (ISF-Former) that facilitates feature exchange between different network stages. By explicitly incorporating color priors and modeling the physical characteristics of underwater image formation, the proposed DUN model achieves more accurate and reliable enhancement results. Extensive experiments on multiple underwater image datasets demonstrate the superiority of the proposed model over state-of-the-art methods in both quantitative and qualitative evaluations. The proposed DUN-based approach offers a promising solution for UIE, enabling more accurate and reliable scientific analysis in marine research. The code is available at https://github.com/CXH-Research/UIE-UnFold. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.10653v1-abstract-full').style.display = 'none'; document.getElementById('2408.10653v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by DSAA CIVIL 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/2407.12255">arXiv:2407.12255</a> <span> [<a href="https://arxiv.org/pdf/2407.12255">pdf</a>, <a href="https://arxiv.org/format/2407.12255">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"> Dual-Hybrid Attention Network for Specular Highlight Removal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Guo%2C+X">Xiaojiao Guo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shenghong Luo</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.12255v1-abstract-short" style="display: inline;"> Specular highlight removal plays a pivotal role in multimedia applications, as it enhances the quality and interpretability of images and videos, ultimately improving the performance of downstream tasks such as content-based retrieval, object recognition, and scene understanding. Despite significant advances in deep learning-based methods, current state-of-the-art approaches often rely on addition… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12255v1-abstract-full').style.display = 'inline'; document.getElementById('2407.12255v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.12255v1-abstract-full" style="display: none;"> Specular highlight removal plays a pivotal role in multimedia applications, as it enhances the quality and interpretability of images and videos, ultimately improving the performance of downstream tasks such as content-based retrieval, object recognition, and scene understanding. Despite significant advances in deep learning-based methods, current state-of-the-art approaches often rely on additional priors or supervision, limiting their practicality and generalization capability. In this paper, we propose the Dual-Hybrid Attention Network for Specular Highlight Removal (DHAN-SHR), an end-to-end network that introduces novel hybrid attention mechanisms to effectively capture and process information across different scales and domains without relying on additional priors or supervision. DHAN-SHR consists of two key components: the Adaptive Local Hybrid-Domain Dual Attention Transformer (L-HD-DAT) and the Adaptive Global Dual Attention Transformer (G-DAT). The L-HD-DAT captures local inter-channel and inter-pixel dependencies while incorporating spectral domain features, enabling the network to effectively model the complex interactions between specular highlights and the underlying surface properties. The G-DAT models global inter-channel relationships and long-distance pixel dependencies, allowing the network to propagate contextual information across the entire image and generate more coherent and consistent highlight-free results. To evaluate the performance of DHAN-SHR and facilitate future research in this area, we compile a large-scale benchmark dataset comprising a diverse range of images with varying levels of specular highlights. Through extensive experiments, we demonstrate that DHAN-SHR outperforms 18 state-of-the-art methods both quantitatively and qualitatively, setting a new standard for specular highlight removal in multimedia applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12255v1-abstract-full').style.display = 'none'; document.getElementById('2407.12255v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by ACM Multimedia 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.18079">arXiv:2406.18079</a> <span> [<a href="https://arxiv.org/pdf/2406.18079">pdf</a>, <a href="https://arxiv.org/format/2406.18079">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+Y">Yiguo Jiang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+W">Wei Feng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.18079v1-abstract-short" style="display: inline;"> When light is scattered or reflected accidentally in the lens, flare artifacts may appear in the captured photos, affecting the photos' visual quality. The main challenge in flare removal is to eliminate various flare artifacts while preserving the original content of the image. To address this challenge, we propose a lightweight Multi-Frequency Deflare Network (MFDNet) based on the Laplacian Pyra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18079v1-abstract-full').style.display = 'inline'; document.getElementById('2406.18079v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.18079v1-abstract-full" style="display: none;"> When light is scattered or reflected accidentally in the lens, flare artifacts may appear in the captured photos, affecting the photos' visual quality. The main challenge in flare removal is to eliminate various flare artifacts while preserving the original content of the image. To address this challenge, we propose a lightweight Multi-Frequency Deflare Network (MFDNet) based on the Laplacian Pyramid. Our network decomposes the flare-corrupted image into low and high-frequency bands, effectively separating the illumination and content information in the image. The low-frequency part typically contains illumination information, while the high-frequency part contains detailed content information. So our MFDNet consists of two main modules: the Low-Frequency Flare Perception Module (LFFPM) to remove flare in the low-frequency part and the Hierarchical Fusion Reconstruction Module (HFRM) to reconstruct the flare-free image. Specifically, to perceive flare from a global perspective while retaining detailed information for image restoration, LFFPM utilizes Transformer to extract global information while utilizing a convolutional neural network to capture detailed local features. Then HFRM gradually fuses the outputs of LFFPM with the high-frequency component of the image through feature aggregation. Moreover, our MFDNet can reduce the computational cost by processing in multiple frequency bands instead of directly removing the flare on the input image. Experimental results demonstrate that our approach outperforms state-of-the-art methods in removing nighttime flare on real-world and synthetic images from the Flare7K dataset. Furthermore, the computational complexity of our model is remarkably low. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18079v1-abstract-full').style.display = 'none'; document.getElementById('2406.18079v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by The Visual Computer journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.10580">arXiv:2406.10580</a> <span> [<a href="https://arxiv.org/pdf/2406.10580">pdf</a>, <a href="https://arxiv.org/format/2406.10580">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"> IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+X">Xiaochen Ma</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+X">Xuekang Zhu</a>, <a href="/search/cs?searchtype=author&query=Su%2C+L">Lei Su</a>, <a href="/search/cs?searchtype=author&query=Du%2C+B">Bo Du</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhuohang Jiang</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+B">Bingkui Tong</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Z">Zeyu Lei</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+X">Xinyu Yang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Lv%2C+J">Jiancheng Lv</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jizhe Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.10580v2-abstract-short" style="display: inline;"> A comprehensive benchmark is yet to be established in the Image Manipulation Detection & Localization (IMDL) field. The absence of such a benchmark leads to insufficient and misleading model evaluations, severely undermining the development of this field. However, the scarcity of open-sourced baseline models and inconsistent training and evaluation protocols make conducting rigorous experiments an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10580v2-abstract-full').style.display = 'inline'; document.getElementById('2406.10580v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10580v2-abstract-full" style="display: none;"> A comprehensive benchmark is yet to be established in the Image Manipulation Detection & Localization (IMDL) field. The absence of such a benchmark leads to insufficient and misleading model evaluations, severely undermining the development of this field. However, the scarcity of open-sourced baseline models and inconsistent training and evaluation protocols make conducting rigorous experiments and faithful comparisons among IMDL models challenging. To address these challenges, we introduce IMDL-BenCo, the first comprehensive IMDL benchmark and modular codebase. IMDL-BenCo: i) decomposes the IMDL framework into standardized, reusable components and revises the model construction pipeline, improving coding efficiency and customization flexibility; ii) fully implements or incorporates training code for state-of-the-art models to establish a comprehensive IMDL benchmark; and iii) conducts deep analysis based on the established benchmark and codebase, offering new insights into IMDL model architecture, dataset characteristics, and evaluation standards. Specifically, IMDL-BenCo includes common processing algorithms, 8 state-of-the-art IMDL models (1 of which are reproduced from scratch), 2 sets of standard training and evaluation protocols, 15 GPU-accelerated evaluation metrics, and 3 kinds of robustness evaluation. This benchmark and codebase represent a significant leap forward in calibrating the current progress in the IMDL field and inspiring future breakthroughs. Code is available at: https://github.com/scu-zjz/IMDLBenCo. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10580v2-abstract-full').style.display = 'none'; document.getElementById('2406.10580v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Technical report, NeurIPS Spotlight of Benchmark and Dataset Track 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.03143">arXiv:2406.03143</a> <span> [<a href="https://arxiv.org/pdf/2406.03143">pdf</a>, <a href="https://arxiv.org/format/2406.03143">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="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> ZeroPur: Succinct Training-Free Adversarial Purification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bi%2C+X">Xiuli Bi</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+Z">Zonglin Yang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo Liu</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Lio%2C+P">Pietro Lio</a>, <a href="/search/cs?searchtype=author&query=Xiao%2C+B">Bin Xiao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.03143v1-abstract-short" style="display: inline;"> Adversarial purification is a kind of defense technique that can defend various unseen adversarial attacks without modifying the victim classifier. Existing methods often depend on external generative models or cooperation between auxiliary functions and victim classifiers. However, retraining generative models, auxiliary functions, or victim classifiers relies on the domain of the fine-tuned data… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03143v1-abstract-full').style.display = 'inline'; document.getElementById('2406.03143v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.03143v1-abstract-full" style="display: none;"> Adversarial purification is a kind of defense technique that can defend various unseen adversarial attacks without modifying the victim classifier. Existing methods often depend on external generative models or cooperation between auxiliary functions and victim classifiers. However, retraining generative models, auxiliary functions, or victim classifiers relies on the domain of the fine-tuned dataset and is computation-consuming. In this work, we suppose that adversarial images are outliers of the natural image manifold and the purification process can be considered as returning them to this manifold. Following this assumption, we present a simple adversarial purification method without further training to purify adversarial images, called ZeroPur. ZeroPur contains two steps: given an adversarial example, Guided Shift obtains the shifted embedding of the adversarial example by the guidance of its blurred counterparts; after that, Adaptive Projection constructs a directional vector by this shifted embedding to provide momentum, projecting adversarial images onto the manifold adaptively. ZeroPur is independent of external models and requires no retraining of victim classifiers or auxiliary functions, relying solely on victim classifiers themselves to achieve purification. Extensive experiments on three datasets (CIFAR-10, CIFAR-100, and ImageNet-1K) using various classifier architectures (ResNet, WideResNet) demonstrate that our method achieves state-of-the-art robust performance. The code will be publicly available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03143v1-abstract-full').style.display = 'none'; document.getElementById('2406.03143v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 5 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/2403.04258">arXiv:2403.04258</a> <span> [<a href="https://arxiv.org/pdf/2403.04258">pdf</a>, <a href="https://arxiv.org/format/2403.04258">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"> Depth-aware Test-Time Training for Zero-shot Video Object Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weihuang Liu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+X">Xi Shen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Haolun Li</a>, <a href="/search/cs?searchtype=author&query=Bi%2C+X">Xiuli Bi</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo Liu</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.04258v1-abstract-short" style="display: inline;"> Zero-shot Video Object Segmentation (ZSVOS) aims at segmenting the primary moving object without any human annotations. Mainstream solutions mainly focus on learning a single model on large-scale video datasets, which struggle to generalize to unseen videos. In this work, we introduce a test-time training (TTT) strategy to address the problem. Our key insight is to enforce the model to predict con… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.04258v1-abstract-full').style.display = 'inline'; document.getElementById('2403.04258v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.04258v1-abstract-full" style="display: none;"> Zero-shot Video Object Segmentation (ZSVOS) aims at segmenting the primary moving object without any human annotations. Mainstream solutions mainly focus on learning a single model on large-scale video datasets, which struggle to generalize to unseen videos. In this work, we introduce a test-time training (TTT) strategy to address the problem. Our key insight is to enforce the model to predict consistent depth during the TTT process. In detail, we first train a single network to perform both segmentation and depth prediction tasks. This can be effectively learned with our specifically designed depth modulation layer. Then, for the TTT process, the model is updated by predicting consistent depth maps for the same frame under different data augmentations. In addition, we explore different TTT weight updating strategies. Our empirical results suggest that the momentum-based weight initialization and looping-based training scheme lead to more stable improvements. Experiments show that the proposed method achieves clear improvements on ZSVOS. Our proposed video TTT strategy provides significant superiority over state-of-the-art TTT methods. Our code is available at: https://nifangbaage.github.io/DATTT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.04258v1-abstract-full').style.display = 'none'; document.getElementById('2403.04258v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by CVPR 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/2402.01422">arXiv:2402.01422</a> <span> [<a href="https://arxiv.org/pdf/2402.01422">pdf</a>, <a href="https://arxiv.org/format/2402.01422">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"> EmoSpeaker: One-shot Fine-grained Emotion-Controlled Talking Face Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Feng%2C+G">Guanwen Feng</a>, <a href="/search/cs?searchtype=author&query=Cheng%2C+H">Haoran Cheng</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yunan Li</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+Z">Zhiyuan Ma</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chaoneng Li</a>, <a href="/search/cs?searchtype=author&query=Qian%2C+Z">Zhihao Qian</a>, <a href="/search/cs?searchtype=author&query=Miao%2C+Q">Qiguang Miao</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.01422v1-abstract-short" style="display: inline;"> Implementing fine-grained emotion control is crucial for emotion generation tasks because it enhances the expressive capability of the generative model, allowing it to accurately and comprehensively capture and express various nuanced emotional states, thereby improving the emotional quality and personalization of generated content. Generating fine-grained facial animations that accurately portray… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01422v1-abstract-full').style.display = 'inline'; document.getElementById('2402.01422v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01422v1-abstract-full" style="display: none;"> Implementing fine-grained emotion control is crucial for emotion generation tasks because it enhances the expressive capability of the generative model, allowing it to accurately and comprehensively capture and express various nuanced emotional states, thereby improving the emotional quality and personalization of generated content. Generating fine-grained facial animations that accurately portray emotional expressions using only a portrait and an audio recording presents a challenge. In order to address this challenge, we propose a visual attribute-guided audio decoupler. This enables the obtention of content vectors solely related to the audio content, enhancing the stability of subsequent lip movement coefficient predictions. To achieve more precise emotional expression, we introduce a fine-grained emotion coefficient prediction module. Additionally, we propose an emotion intensity control method using a fine-grained emotion matrix. Through these, effective control over emotional expression in the generated videos and finer classification of emotion intensity are accomplished. Subsequently, a series of 3DMM coefficient generation networks are designed to predict 3D coefficients, followed by the utilization of a rendering network to generate the final video. Our experimental results demonstrate that our proposed method, EmoSpeaker, outperforms existing emotional talking face generation methods in terms of expression variation and lip synchronization. Project page: https://peterfanfan.github.io/EmoSpeaker/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01422v1-abstract-full').style.display = 'none'; document.getElementById('2402.01422v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.05614">arXiv:2401.05614</a> <span> [<a href="https://arxiv.org/pdf/2401.05614">pdf</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="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"> Self-Attention and Hybrid Features for Replay and Deep-Fake Audio Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+L">Lian Huang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2401.05614v1-abstract-short" style="display: inline;"> Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker verification system is still vulnerable to spoofing attacks such as replay or Deep-Fake audio. Deep-Fake audio means that the spoofed utterances are generated u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05614v1-abstract-full').style.display = 'inline'; document.getElementById('2401.05614v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.05614v1-abstract-full" style="display: none;"> Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker verification system is still vulnerable to spoofing attacks such as replay or Deep-Fake audio. Deep-Fake audio means that the spoofed utterances are generated using text-to-speech (TTS) and voice conversion (VC) algorithms. Here, we propose a novel framework based on hybrid features with the self-attention mechanism. It is expected that hybrid features can be used to get more discrimination capacity. Firstly, instead of only one type of conventional feature, deep learning features and Mel-spectrogram features will be extracted by two parallel paths: convolution neural networks and a short-time Fourier transform (STFT) followed by Mel-frequency. Secondly, features will be concatenated by a max-pooling layer. Thirdly, there is a Self-attention mechanism for focusing on essential elements. Finally, ResNet and a linear layer are built to get the results. Experimental results reveal that the hybrid features, compared with conventional features, can cover more details of an utterance. We achieve the best Equal Error Rate (EER) of 9.67\% in the physical access (PA) scenario and 8.94\% in the Deep fake task on the ASVspoof 2021 dataset. Compared with the best baseline system, the proposed approach improves by 74.60\% and 60.05\%, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05614v1-abstract-full').style.display = 'none'; document.getElementById('2401.05614v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.00268">arXiv:2401.00268</a> <span> [<a href="https://arxiv.org/pdf/2401.00268">pdf</a>, <a href="https://arxiv.org/format/2401.00268">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"> COMMA: Co-Articulated Multi-Modal Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+L">Lianyu Hu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+L">Liqing Gao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zekang Liu</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+W">Wei Feng</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="2401.00268v1-abstract-short" style="display: inline;"> Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt templates to achieve satisfactory performance. Recently, various methods have been proposed to dynamically learn the prompts as the textual inputs to avoid the req… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.00268v1-abstract-full').style.display = 'inline'; document.getElementById('2401.00268v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.00268v1-abstract-full" style="display: none;"> Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt templates to achieve satisfactory performance. Recently, various methods have been proposed to dynamically learn the prompts as the textual inputs to avoid the requirements of laboring hand-crafted prompt engineering in the fine-tuning process. We notice that these methods are suboptimal in two aspects. First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated. Thus, the prompts of both branches are not fully correlated and may not provide enough guidance to align the representations of both branches. Second, it's observed that most previous methods usually achieve better performance on seen classes but cause performance degeneration on unseen classes compared to CLIP. This is because the essential generic knowledge learned in the pretraining stage is partly forgotten in the fine-tuning process. In this paper, we propose Co-Articulated Multi-Modal Learning (COMMA) to handle the above limitations. Especially, our method considers prompts from both branches to generate the prompts to enhance the representation alignment of both branches. Besides, to alleviate forgetting about the essential knowledge, we minimize the feature discrepancy between the learned prompts and the embeddings of hand-crafted prompts in the pre-trained CLIP in the late transformer layers. We evaluate our method across three representative tasks of generalization to novel classes, new target datasets and unseen domain shifts. Experimental results demonstrate the superiority of our method by exhibiting a favorable performance boost upon all tasks with high efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.00268v1-abstract-full').style.display = 'none'; document.getElementById('2401.00268v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 December, 2023; <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 AAAI2024. Code is available at https://github.com/hulianyuyy/COMMA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.14141">arXiv:2312.14141</a> <span> [<a href="https://arxiv.org/pdf/2312.14141">pdf</a>, <a href="https://arxiv.org/format/2312.14141">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> Quantum Algorithms for the Pathwise Lasso </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Doriguello%2C+J+F">Joao F. Doriguello</a>, <a href="/search/cs?searchtype=author&query=Lim%2C+D">Debbie Lim</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C+S">Chi Seng Pun</a>, <a href="/search/cs?searchtype=author&query=Rebentrost%2C+P">Patrick Rebentrost</a>, <a href="/search/cs?searchtype=author&query=Vaidya%2C+T">Tushar Vaidya</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.14141v2-abstract-short" style="display: inline;"> We present a novel quantum high-dimensional linear regression algorithm with an $\ell_1$-penalty based on the classical LARS (Least Angle Regression) pathwise algorithm. Similarly to available classical algorithms for Lasso, our quantum algorithm provides the full regularisation path as the penalty term varies, but quadratically faster per iteration under specific conditions. A quadratic speedup o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.14141v2-abstract-full').style.display = 'inline'; document.getElementById('2312.14141v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.14141v2-abstract-full" style="display: none;"> We present a novel quantum high-dimensional linear regression algorithm with an $\ell_1$-penalty based on the classical LARS (Least Angle Regression) pathwise algorithm. Similarly to available classical algorithms for Lasso, our quantum algorithm provides the full regularisation path as the penalty term varies, but quadratically faster per iteration under specific conditions. A quadratic speedup on the number of features $d$ is possible by using the quantum minimum-finding routine from D眉rr and Hoyer (arXiv'96) in order to obtain the joining time at each iteration. We then improve upon this simple quantum algorithm and obtain a quadratic speedup both in the number of features $d$ and the number of observations $n$ by using the approximate quantum minimum-finding routine from Chen and de Wolf (ICALP'23). As one of our main contributions, we construct a quantum unitary to approximately compute the joining times to be searched over by the approximate quantum minimum finding. Since the joining times are no longer exactly computed, it is no longer clear that the resulting approximate quantum algorithm obtains a good solution. As our second main contribution, we prove, via an approximate version of the KKT conditions and a duality gap, that the LARS algorithm (and thus our quantum algorithm) is robust to errors. This means that it still outputs a path that minimises the Lasso cost function up to a small error if the joining times are approximately computed. Moreover, we show that, when the observations are sampled from a Gaussian distribution, our quantum algorithm's complexity only depends polylogarithmically on $n$, exponentially better than the classical LARS algorithm, while keeping the quadratic improvement on $d$. Finally, we propose a dequantised algorithm that also retains the polylogarithmic dependence on $n$, albeit with the linear scaling on $d$ from the standard LARS algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.14141v2-abstract-full').style.display = 'none'; document.getElementById('2312.14141v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">48 pages. v2: several improvements, typos fixed, references added, fixed a bug in Theorem 28, exponentially improved the complexity dependence on the number of observations $n$ for a random Gaussian input matrix</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.01632">arXiv:2312.01632</a> <span> [<a href="https://arxiv.org/pdf/2312.01632">pdf</a>, <a href="https://arxiv.org/format/2312.01632">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"> GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jie Wang</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+J">Jiu-Cheng Xie</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xianyan Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+F">Feng Xu</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+H">Hao Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2312.01632v4-abstract-short" style="display: inline;"> Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging. This paper presents GaussianHead, which models the actional human head with anisotropic 3D Gaussians. In our framework, a motion deformation field and multi-resolution tri-plane are constructed respectively to deal with the head's dynamic geometry and complex texture. Not… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.01632v4-abstract-full').style.display = 'inline'; document.getElementById('2312.01632v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.01632v4-abstract-full" style="display: none;"> Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging. This paper presents GaussianHead, which models the actional human head with anisotropic 3D Gaussians. In our framework, a motion deformation field and multi-resolution tri-plane are constructed respectively to deal with the head's dynamic geometry and complex texture. Notably, we impose an exclusive derivation scheme on each Gaussian, which generates its multiple doppelgangers through a set of learnable parameters for position transformation. With this design, we can compactly and accurately encode the appearance information of Gaussians, even those fitting the head's particular components with sophisticated structures. In addition, an inherited derivation strategy for newly added Gaussians is adopted to facilitate training acceleration. Extensive experiments show that our method can produce high-fidelity renderings, outperforming state-of-the-art approaches in reconstruction, cross-identity reenactment, and novel view synthesis tasks. Our code is available at: https://github.com/chiehwangs/gaussian-head. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.01632v4-abstract-full').style.display = 'none'; document.getElementById('2312.01632v4-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.15306">arXiv:2311.15306</a> <span> [<a href="https://arxiv.org/pdf/2311.15306">pdf</a>, <a href="https://arxiv.org/format/2311.15306">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> </div> </div> <p class="title is-5 mathjax"> Sketch Video Synthesis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+Y">Yudian Zheng</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+M">Menghan Xia</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2311.15306v1-abstract-short" style="display: inline;"> Understanding semantic intricacies and high-level concepts is essential in image sketch generation, and this challenge becomes even more formidable when applied to the domain of videos. To address this, we propose a novel optimization-based framework for sketching videos represented by the frame-wise B茅zier curve. In detail, we first propose a cross-frame stroke initialization approach to warm up… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.15306v1-abstract-full').style.display = 'inline'; document.getElementById('2311.15306v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.15306v1-abstract-full" style="display: none;"> Understanding semantic intricacies and high-level concepts is essential in image sketch generation, and this challenge becomes even more formidable when applied to the domain of videos. To address this, we propose a novel optimization-based framework for sketching videos represented by the frame-wise B茅zier curve. In detail, we first propose a cross-frame stroke initialization approach to warm up the location and the width of each curve. Then, we optimize the locations of these curves by utilizing a semantic loss based on CLIP features and a newly designed consistency loss using the self-decomposed 2D atlas network. Built upon these design elements, the resulting sketch video showcases impressive visual abstraction and temporal coherence. Furthermore, by transforming a video into SVG lines through the sketching process, our method unlocks applications in sketch-based video editing and video doodling, enabled through video composition, as exemplified in the teaser. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.15306v1-abstract-full').style.display = 'none'; document.getElementById('2311.15306v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Webpage: https://sketchvideo.github.io/ Github: https://github.com/yudianzheng/SketchVideo</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.08032">arXiv:2311.08032</a> <span> [<a href="https://arxiv.org/pdf/2311.08032">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> ELF: An End-to-end Local and Global Multimodal Fusion Framework for Glaucoma Grading </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenyun Li</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2311.08032v1-abstract-short" style="display: inline;"> Glaucoma is a chronic neurodegenerative condition that can lead to blindness. Early detection and curing are very important in stopping the disease from getting worse for glaucoma patients. The 2D fundus images and optical coherence tomography(OCT) are useful for ophthalmologists in diagnosing glaucoma. There are many methods based on the fundus images or 3D OCT volumes; however, the mining for mu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08032v1-abstract-full').style.display = 'inline'; document.getElementById('2311.08032v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.08032v1-abstract-full" style="display: none;"> Glaucoma is a chronic neurodegenerative condition that can lead to blindness. Early detection and curing are very important in stopping the disease from getting worse for glaucoma patients. The 2D fundus images and optical coherence tomography(OCT) are useful for ophthalmologists in diagnosing glaucoma. There are many methods based on the fundus images or 3D OCT volumes; however, the mining for multi-modality, including both fundus images and data, is less studied. In this work, we propose an end-to-end local and global multi-modal fusion framework for glaucoma grading, named ELF for short. ELF can fully utilize the complementary information between fundus and OCT. In addition, unlike previous methods that concatenate the multi-modal features together, which lack exploring the mutual information between different modalities, ELF can take advantage of local-wise and global-wise mutual information. The extensive experiment conducted on the multi-modal glaucoma grading GAMMA dataset can prove the effiectness of ELF when compared with other state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.08032v1-abstract-full').style.display = 'none'; document.getElementById('2311.08032v1-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.20210">arXiv:2310.20210</a> <span> [<a href="https://arxiv.org/pdf/2310.20210">pdf</a>, <a href="https://arxiv.org/format/2310.20210">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"> UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weiwen Chen</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Y">Yingtie Lei</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shenghong Luo</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Ziyang Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+M">Mingxian Li</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.20210v4-abstract-short" style="display: inline;"> Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement techniques, there exist several problems that demand further improvement: (i) The current deep learning methods rely on Convolutional Neural Networks (CNNs) that lack… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.20210v4-abstract-full').style.display = 'inline'; document.getElementById('2310.20210v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.20210v4-abstract-full" style="display: none;"> Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement techniques, there exist several problems that demand further improvement: (i) The current deep learning methods rely on Convolutional Neural Networks (CNNs) that lack the multi-scale enhancement, and global perception field is also limited. (ii) The scarcity of paired real-world underwater datasets poses a significant challenge, and the utilization of synthetic image pairs could lead to overfitting. To address the aforementioned problems, this paper introduces a Multi-scale Transformer-based Network called UWFormer for enhancing images at multiple frequencies via semi-supervised learning, in which we propose a Nonlinear Frequency-aware Attention mechanism and a Multi-Scale Fusion Feed-forward Network for low-frequency enhancement. Besides, we introduce a special underwater semi-supervised training strategy, where we propose a Subaqueous Perceptual Loss function to generate reliable pseudo labels. Experiments using full-reference and non-reference underwater benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of both quantity and visual quality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.20210v4-abstract-full').style.display = 'none'; document.getElementById('2310.20210v4-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IJCNN 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/2310.06525">arXiv:2310.06525</a> <span> [<a href="https://arxiv.org/pdf/2310.06525">pdf</a>, <a href="https://arxiv.org/format/2310.06525">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"> Perceptual MAE for Image Manipulation Localization: A High-level Vision Learner Focusing on Low-level Features </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ma%2C+X">Xiaochen Ma</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+J">Jizhe Zhou</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+X">Xiong Xu</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zhuohang Jiang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.06525v1-abstract-short" style="display: inline;"> Nowadays, multimedia forensics faces unprecedented challenges due to the rapid advancement of multimedia generation technology thereby making Image Manipulation Localization (IML) crucial in the pursuit of truth. The key to IML lies in revealing the artifacts or inconsistencies between the tampered and authentic areas, which are evident under pixel-level features. Consequently, existing studies tr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.06525v1-abstract-full').style.display = 'inline'; document.getElementById('2310.06525v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.06525v1-abstract-full" style="display: none;"> Nowadays, multimedia forensics faces unprecedented challenges due to the rapid advancement of multimedia generation technology thereby making Image Manipulation Localization (IML) crucial in the pursuit of truth. The key to IML lies in revealing the artifacts or inconsistencies between the tampered and authentic areas, which are evident under pixel-level features. Consequently, existing studies treat IML as a low-level vision task, focusing on allocating tampered masks by crafting pixel-level features such as image RGB noises, edge signals, or high-frequency features. However, in practice, tampering commonly occurs at the object level, and different classes of objects have varying likelihoods of becoming targets of tampering. Therefore, object semantics are also vital in identifying the tampered areas in addition to pixel-level features. This necessitates IML models to carry out a semantic understanding of the entire image. In this paper, we reformulate the IML task as a high-level vision task that greatly benefits from low-level features. Based on such an interpretation, we propose a method to enhance the Masked Autoencoder (MAE) by incorporating high-resolution inputs and a perceptual loss supervision module, which is termed Perceptual MAE (PMAE). While MAE has demonstrated an impressive understanding of object semantics, PMAE can also compensate for low-level semantics with our proposed enhancements. Evidenced by extensive experiments, this paradigm effectively unites the low-level and high-level features of the IML task and outperforms state-of-the-art tampering localization methods on all five publicly available datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.06525v1-abstract-full').style.display = 'none'; document.getElementById('2310.06525v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.02663">arXiv:2310.02663</a> <span> [<a href="https://arxiv.org/pdf/2310.02663">pdf</a>, <a href="https://arxiv.org/format/2310.02663">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"> MedPrompt: Cross-Modal Prompting for Multi-Task Medical Image Translation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.02663v1-abstract-short" style="display: inline;"> Cross-modal medical image translation is an essential task for synthesizing missing modality data for clinical diagnosis. However, current learning-based techniques have limitations in capturing cross-modal and global features, restricting their suitability to specific pairs of modalities. This lack of versatility undermines their practical usefulness, particularly considering that the missing mod… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.02663v1-abstract-full').style.display = 'inline'; document.getElementById('2310.02663v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.02663v1-abstract-full" style="display: none;"> Cross-modal medical image translation is an essential task for synthesizing missing modality data for clinical diagnosis. However, current learning-based techniques have limitations in capturing cross-modal and global features, restricting their suitability to specific pairs of modalities. This lack of versatility undermines their practical usefulness, particularly considering that the missing modality may vary for different cases. In this study, we present MedPrompt, a multi-task framework that efficiently translates different modalities. Specifically, we propose the Self-adaptive Prompt Block, which dynamically guides the translation network towards distinct modalities. Within this framework, we introduce the Prompt Extraction Block and the Prompt Fusion Block to efficiently encode the cross-modal prompt. To enhance the extraction of global features across diverse modalities, we incorporate the Transformer model. Extensive experimental results involving five datasets and four pairs of modalities demonstrate that our proposed model achieves state-of-the-art visual quality and exhibits excellent generalization capability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.02663v1-abstract-full').style.display = 'none'; document.getElementById('2310.02663v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.06670">arXiv:2309.06670</a> <span> [<a href="https://arxiv.org/pdf/2309.06670">pdf</a>, <a href="https://arxiv.org/format/2309.06670">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"> ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weiwen Chen</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Y">Yingtie Lei</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shenghong Luo</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Ziyang Zhou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+M">Mingxian Li</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.06670v4-abstract-short" style="display: inline;"> Document shadow is a common issue that arises when capturing documents using mobile devices, which significantly impacts readability. Current methods encounter various challenges, including inaccurate detection of shadow masks and estimation of illumination. In this paper, we propose ShaDocFormer, a Transformer-based architecture that integrates traditional methodologies and deep learning techniqu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.06670v4-abstract-full').style.display = 'inline'; document.getElementById('2309.06670v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.06670v4-abstract-full" style="display: none;"> Document shadow is a common issue that arises when capturing documents using mobile devices, which significantly impacts readability. Current methods encounter various challenges, including inaccurate detection of shadow masks and estimation of illumination. In this paper, we propose ShaDocFormer, a Transformer-based architecture that integrates traditional methodologies and deep learning techniques to tackle the problem of document shadow removal. The ShaDocFormer architecture comprises two components: the Shadow-attentive Threshold Detector (STD) and the Cascaded Fusion Refiner (CFR). The STD module employs a traditional thresholding technique and leverages the attention mechanism of the Transformer to gather global information, thereby enabling precise detection of shadow masks. The cascaded and aggregative structure of the CFR module facilitates a coarse-to-fine restoration process for the entire image. As a result, ShaDocFormer excels in accurately detecting and capturing variations in both shadow and illumination, thereby enabling effective removal of shadows. Extensive experiments demonstrate that ShaDocFormer outperforms current state-of-the-art methods in both qualitative and quantitative measurements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.06670v4-abstract-full').style.display = 'none'; document.getElementById('2309.06670v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IJCNN 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/2308.14221">arXiv:2308.14221</a> <span> [<a href="https://arxiv.org/pdf/2308.14221">pdf</a>, <a href="https://arxiv.org/format/2308.14221">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"> High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zinuo Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</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="2308.14221v4-abstract-short" style="display: inline;"> Shadows often occur when we capture the documents with casual equipment, which influences the visual quality and readability of the digital copies. Different from the algorithms for natural shadow removal, the algorithms in document shadow removal need to preserve the details of fonts and figures in high-resolution input. Previous works ignore this problem and remove the shadows via approximate at… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.14221v4-abstract-full').style.display = 'inline'; document.getElementById('2308.14221v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.14221v4-abstract-full" style="display: none;"> Shadows often occur when we capture the documents with casual equipment, which influences the visual quality and readability of the digital copies. Different from the algorithms for natural shadow removal, the algorithms in document shadow removal need to preserve the details of fonts and figures in high-resolution input. Previous works ignore this problem and remove the shadows via approximate attention and small datasets, which might not work in real-world situations. We handle high-resolution document shadow removal directly via a larger-scale real-world dataset and a carefully designed frequency-aware network. As for the dataset, we acquire over 7k couples of high-resolution (2462 x 3699) images of real-world document pairs with various samples under different lighting circumstances, which is 10 times larger than existing datasets. As for the design of the network, we decouple the high-resolution images in the frequency domain, where the low-frequency details and high-frequency boundaries can be effectively learned via the carefully designed network structure. Powered by our network and dataset, the proposed method clearly shows a better performance than previous methods in terms of visual quality and numerical results. The code, models, and dataset are available at: https://github.com/CXH-Research/DocShadow-SD7K <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.14221v4-abstract-full').style.display = 'none'; document.getElementById('2308.14221v4-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by International Conference on Computer Vision 2023 (ICCV 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.13739">arXiv:2308.13739</a> <span> [<a href="https://arxiv.org/pdf/2308.13739">pdf</a>, <a href="https://arxiv.org/format/2308.13739">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer With Adaptive Channel Expansion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shenghong Luo</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+W">Weiwen Chen</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zinuo Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2308.13739v2-abstract-short" style="display: inline;"> Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13739v2-abstract-full').style.display = 'inline'; document.getElementById('2308.13739v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.13739v2-abstract-full" style="display: none;"> Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in the ineffective removal of irregular vignetting and suboptimal results. Moreover, the substantial lack of real-world vignetting datasets hinders the objective and comprehensive evaluation of vignetting removal. To address these challenges, we present Vigset, a pioneering dataset for vignetting removal. Vigset includes 983 pairs of both vignetting and vignetting-free high-resolution ($5340\times3697$) real-world images under various conditions. In addition, We introduce DeVigNet, a novel frequency-aware Transformer architecture designed for vignetting removal. Through the Laplacian Pyramid decomposition, we propose the Dual Aggregated Fusion Transformer to handle global features and remove vignetting in the low-frequency domain. Additionally, we propose the Adaptive Channel Expansion Module to enhance details in the high-frequency domain. The experiments demonstrate that the proposed model outperforms existing state-of-the-art methods. The code, models, and dataset are available at \url{https://github.com/CXH-Research/DeVigNet}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.13739v2-abstract-full').style.display = 'none'; document.getElementById('2308.13739v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by AAAI Conference on Artificial Intelligence 2024 (AAAI 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/2308.11029">arXiv:2308.11029</a> <span> [<a href="https://arxiv.org/pdf/2308.11029">pdf</a>, <a href="https://arxiv.org/format/2308.11029">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div 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/TASLP.2023.3284509">10.1109/TASLP.2023.3284509 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> RBA-GCN: Relational Bilevel Aggregation Graph Convolutional Network for Emotion Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yuan%2C+L">Lin Yuan</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Guoheng Huang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+F">Fenghuan Li</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xiaochen Yuan</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+G">Guo Zhong</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="2308.11029v2-abstract-short" style="display: inline;"> Emotion recognition in conversation (ERC) has received increasing attention from researchers due to its wide range of applications.As conversation has a natural graph structure,numerous approaches used to model ERC based on graph convolutional networks (GCNs) have yielded significant results.However,the aggregation approach of traditional GCNs suffers from the node information redundancy problem,l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11029v2-abstract-full').style.display = 'inline'; document.getElementById('2308.11029v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.11029v2-abstract-full" style="display: none;"> Emotion recognition in conversation (ERC) has received increasing attention from researchers due to its wide range of applications.As conversation has a natural graph structure,numerous approaches used to model ERC based on graph convolutional networks (GCNs) have yielded significant results.However,the aggregation approach of traditional GCNs suffers from the node information redundancy problem,leading to node discriminant information loss.Additionally,single-layer GCNs lack the capacity to capture long-range contextual information from the graph. Furthermore,the majority of approaches are based on textual modality or stitching together different modalities, resulting in a weak ability to capture interactions between modalities. To address these problems, we present the relational bilevel aggregation graph convolutional network (RBA-GCN), which consists of three modules: the graph generation module (GGM), similarity-based cluster building module (SCBM) and bilevel aggregation module (BiAM). First, GGM constructs a novel graph to reduce the redundancy of target node information.Then,SCBM calculates the node similarity in the target node and its structural neighborhood, where noisy information with low similarity is filtered out to preserve the discriminant information of the node. Meanwhile, BiAM is a novel aggregation method that can preserve the information of nodes during the aggregation process. This module can construct the interaction between different modalities and capture long-range contextual information based on similarity clusters. On both the IEMOCAP and MELD datasets, the weighted average F1 score of RBA-GCN has a 2.17$\sim$5.21\% improvement over that of the most advanced method.Our code is available at https://github.com/luftmenscher/RBA-GCN and our article with the same name has been published in IEEE/ACM Transactions on Audio,Speech,and Language Processing,vol.31,2023 <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11029v2-abstract-full').style.display = 'none'; document.getElementById('2308.11029v2-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 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">Journal ref:</span> IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2325-2337,2023 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.08327">arXiv:2308.08327</a> <span> [<a href="https://arxiv.org/pdf/2308.08327">pdf</a>, <a href="https://arxiv.org/format/2308.08327">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"> AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+L">Lianyu Hu</a>, <a href="/search/cs?searchtype=author&query=Gao%2C+L">Liqing Gao</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zekang Liu</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Feng%2C+W">Wei Feng</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="2308.08327v1-abstract-short" style="display: inline;"> Raw videos have been proven to own considerable feature redundancy where in many cases only a portion of frames can already meet the requirements for accurate recognition. In this paper, we are interested in whether such redundancy can be effectively leveraged to facilitate efficient inference in continuous sign language recognition (CSLR). We propose a novel adaptive model (AdaBrowse) to dynamica… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08327v1-abstract-full').style.display = 'inline'; document.getElementById('2308.08327v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.08327v1-abstract-full" style="display: none;"> Raw videos have been proven to own considerable feature redundancy where in many cases only a portion of frames can already meet the requirements for accurate recognition. In this paper, we are interested in whether such redundancy can be effectively leveraged to facilitate efficient inference in continuous sign language recognition (CSLR). We propose a novel adaptive model (AdaBrowse) to dynamically select a most informative subsequence from input video sequences by modelling this problem as a sequential decision task. In specific, we first utilize a lightweight network to quickly scan input videos to extract coarse features. Then these features are fed into a policy network to intelligently select a subsequence to process. The corresponding subsequence is finally inferred by a normal CSLR model for sentence prediction. As only a portion of frames are processed in this procedure, the total computations can be considerably saved. Besides temporal redundancy, we are also interested in whether the inherent spatial redundancy can be seamlessly integrated together to achieve further efficiency, i.e., dynamically selecting a lowest input resolution for each sample, whose model is referred to as AdaBrowse+. Extensive experimental results on four large-scale CSLR datasets, i.e., PHOENIX14, PHOENIX14-T, CSL-Daily and CSL, demonstrate the effectiveness of AdaBrowse and AdaBrowse+ by achieving comparable accuracy with state-of-the-art methods with 1.44$\times$ throughput and 2.12$\times$ fewer FLOPs. Comparisons with other commonly-used 2D CNNs and adaptive efficient methods verify the effectiveness of AdaBrowse. Code is available at \url{https://github.com/hulianyuyy/AdaBrowse}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.08327v1-abstract-full').style.display = 'none'; document.getElementById('2308.08327v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ACMMM2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.15318">arXiv:2307.15318</a> <span> [<a href="https://arxiv.org/pdf/2307.15318">pdf</a>, <a href="https://arxiv.org/format/2307.15318">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"> DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhou%2C+Z">Ziyang Zhou</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Y">Yingtie Lei</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Luo%2C+S">Shenghong Luo</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+W">Wenjun Zhang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhen Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.15318v2-abstract-short" style="display: inline;"> Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability. Current shadow removal techniques, including traditional methods and deep learning approaches, face limitations in handling varying shadow intensities and preserving document details. To address these issues, we propose DocDeshadower,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15318v2-abstract-full').style.display = 'inline'; document.getElementById('2307.15318v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.15318v2-abstract-full" style="display: none;"> Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability. Current shadow removal techniques, including traditional methods and deep learning approaches, face limitations in handling varying shadow intensities and preserving document details. To address these issues, we propose DocDeshadower, a novel multi-frequency Transformer-based model built upon the Laplacian Pyramid. By decomposing the shadow image into multiple frequency bands and employing two critical modules: the Attention-Aggregation Network for low-frequency shadow removal and the Gated Multi-scale Fusion Transformer for global refinement. DocDeshadower effectively removes shadows at different scales while preserving document content. Extensive experiments demonstrate DocDeshadower's superior performance compared to state-of-the-art methods, highlighting its potential to significantly improve document shadow removal techniques. The code is available at https://github.com/leiyingtie/DocDeshadower. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.15318v2-abstract-full').style.display = 'none'; document.getElementById('2307.15318v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE International Conference on Systems, Man, and Cybernetics 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/2306.11322">arXiv:2306.11322</a> <span> [<a href="https://arxiv.org/pdf/2306.11322">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Reversible Adversarial Examples with Beam Search Attack and Grayscale Invariance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+H">Haodong Zhang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C+M">Chi Man Pun</a>, <a href="/search/cs?searchtype=author&query=Du%2C+X">Xia Du</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.11322v1-abstract-short" style="display: inline;"> Reversible adversarial examples (RAE) combine adversarial attacks and reversible data-hiding technology on a single image to prevent illegal access. Most RAE studies focus on achieving white-box attacks. In this paper, we propose a novel framework to generate reversible adversarial examples, which combines a novel beam search based black-box attack and reversible data hiding with grayscale invaria… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.11322v1-abstract-full').style.display = 'inline'; document.getElementById('2306.11322v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.11322v1-abstract-full" style="display: none;"> Reversible adversarial examples (RAE) combine adversarial attacks and reversible data-hiding technology on a single image to prevent illegal access. Most RAE studies focus on achieving white-box attacks. In this paper, we propose a novel framework to generate reversible adversarial examples, which combines a novel beam search based black-box attack and reversible data hiding with grayscale invariance (RDH-GI). This RAE uses beam search to evaluate the adversarial gain of historical perturbations and guide adversarial perturbations. After the adversarial examples are generated, the framework RDH-GI embeds the secret data that can be recovered losslessly. Experimental results show that our method can achieve an average Peak Signal-to-Noise Ratio (PSNR) of at least 40dB compared to source images with limited query budgets. Our method can also achieve a targeted black-box reversible adversarial attack for the first time. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.11322v1-abstract-full').style.display = 'none'; document.getElementById('2306.11322v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to ICICS2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.18476">arXiv:2305.18476</a> <span> [<a href="https://arxiv.org/pdf/2305.18476">pdf</a>, <a href="https://arxiv.org/format/2305.18476">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"> Explicit Visual Prompting for Universal Foreground Segmentations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weihuang Liu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+X">Xi Shen</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.18476v1-abstract-short" style="display: inline;"> Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied on domain-specific solutions to address accuracy and robustness issues in those applications. In this paper, we present a unified framework for a number of for… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.18476v1-abstract-full').style.display = 'inline'; document.getElementById('2305.18476v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.18476v1-abstract-full" style="display: none;"> Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied on domain-specific solutions to address accuracy and robustness issues in those applications. In this paper, we present a unified framework for a number of foreground segmentation tasks without any task-specific designs. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and high-frequency components. Our method freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters. Despite introducing only a small number of tunable parameters, EVP achieves superior performance than full fine-tuning and other parameter-efficient fine-tuning methods. Experiments in fourteen datasets across five tasks show the proposed method outperforms other task-specific methods while being considerably simple. The proposed method demonstrates the scalability in different architectures, pre-trained weights, and tasks. The code is available at: https://github.com/NiFangBaAGe/Explicit-Visual-Prompt. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.18476v1-abstract-full').style.display = 'none'; document.getElementById('2305.18476v1-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: substantial text overlap with arXiv:2303.10883</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.10754">arXiv:2305.10754</a> <span> [<a href="https://arxiv.org/pdf/2305.10754">pdf</a>, <a href="https://arxiv.org/format/2305.10754">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"> Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zuo%2C+Q">Qiankun Zuo</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+H">Hao Tian</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Hongfei Wang</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yudong Zhang</a>, <a href="/search/cs?searchtype=author&query=Hong%2C+J">Jin Hong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.10754v2-abstract-short" style="display: inline;"> Effective connectivity can describe the causal patterns among brain regions. These patterns have the potential to reveal the pathological mechanism and promote early diagnosis and effective drug development for cognitive disease. However, the current methods utilize software toolkits to extract empirical features from brain imaging to estimate effective connectivity. These methods heavily rely on… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10754v2-abstract-full').style.display = 'inline'; document.getElementById('2305.10754v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.10754v2-abstract-full" style="display: none;"> Effective connectivity can describe the causal patterns among brain regions. These patterns have the potential to reveal the pathological mechanism and promote early diagnosis and effective drug development for cognitive disease. However, the current methods utilize software toolkits to extract empirical features from brain imaging to estimate effective connectivity. These methods heavily rely on manual parameter settings and may result in large errors during effective connectivity estimation. In this paper, a novel brain imaging-to-graph generation (BIGG) framework is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment (MCI) analysis. To be specific, the proposed BIGG framework is based on the diffusion denoising probabilistic models (DDPM), where each denoising step is modeled as a generative adversarial network (GAN) to progressively translate the noise and conditional fMRI to effective connectivity. The hierarchical transformers in the generator are designed to estimate the noise at multiple scales. Each scale concentrates on both spatial and temporal information between brain regions, enabling good quality in noise removal and better inference of causal relations. Meanwhile, the transformer-based discriminator constrains the generator to further capture global and local patterns for improving high-quality and diversity generation. By introducing the diffusive factor, the denoising inference with a large sampling step size is more efficient and can maintain high-quality results for effective connectivity generation. Evaluations of the ADNI dataset demonstrate the feasibility and efficacy of the proposed model. The proposed model not only achieves superior prediction performance compared with other competing methods but also predicts MCI-related causal connections that are consistent with clinical studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10754v2-abstract-full').style.display = 'none'; document.getElementById('2305.10754v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 12 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.07283">arXiv:2305.07283</a> <span> [<a href="https://arxiv.org/pdf/2305.07283">pdf</a>, <a href="https://arxiv.org/format/2305.07283">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TCSVT.2022.3223150">10.1109/TCSVT.2022.3223150 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zewen Zheng</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+G">Guoheng Huang</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xiaochen Yuan</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+H">Hongrui Liu</a>, <a href="/search/cs?searchtype=author&query=Ling%2C+W">Wing-Kuen Ling</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.07283v3-abstract-short" style="display: inline;"> Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Encouraging progress has been made for FSS by leveraging semantic features learned from base classes with sufficient training samples to represent novel classes. The correlation-based methods lack the ability to consider interaction of the two subspace matching scores due to the inherent nature of the re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07283v3-abstract-full').style.display = 'inline'; document.getElementById('2305.07283v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.07283v3-abstract-full" style="display: none;"> Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Encouraging progress has been made for FSS by leveraging semantic features learned from base classes with sufficient training samples to represent novel classes. The correlation-based methods lack the ability to consider interaction of the two subspace matching scores due to the inherent nature of the real-valued 2D convolutions. In this paper, we introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet), with the aim to alleviate the computational burden of high-dimensional correlation tensor and explore internal latent interaction between query and support images by leveraging operations defined by the established quaternion algebra. Specifically, our QCLNet is formulated as a hyper-complex valued network and represents correlation tensors in the quaternion domain, which uses quaternion-valued convolution to explore the external relations of query subspace when considering the hidden relationship of the support sub-dimension in the quaternion space. Extensive experiments on the PASCAL-5i and COCO-20i datasets demonstrate that our method outperforms the existing state-of-the-art methods effectively. Our code is available at https://github.com/zwzheng98/QCLNet and our article "Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation" was published in IEEE Transactions on Circuits and Systems for Video Technology, vol. 33,no.5,pp.2102-2115,May 2023,doi: 10.1109/TCSVT.2022.3223150. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.07283v3-abstract-full').style.display = 'none'; document.getElementById('2305.07283v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">for associated paper file, see https://ieeexplore.ieee.org/document/9954424?source=authoralert</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2304.04368">arXiv:2304.04368</a> <span> [<a href="https://arxiv.org/pdf/2304.04368">pdf</a>, <a href="https://arxiv.org/format/2304.04368">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"> Locality Preserving Multiview Graph Hashing for Large Scale Remote Sensing Image Search </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenyun Li</a>, <a href="/search/cs?searchtype=author&query=Zhong%2C+G">Guo Zhong</a>, <a href="/search/cs?searchtype=author&query=Lu%2C+X">Xingyu Lu</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2304.04368v1-abstract-short" style="display: inline;"> Hashing is very popular for remote sensing image search. This article proposes a multiview hashing with learnable parameters to retrieve the queried images for a large-scale remote sensing dataset. Existing methods always neglect that real-world remote sensing data lies on a low-dimensional manifold embedded in high-dimensional ambient space. Unlike previous methods, this article proposes to learn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.04368v1-abstract-full').style.display = 'inline'; document.getElementById('2304.04368v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.04368v1-abstract-full" style="display: none;"> Hashing is very popular for remote sensing image search. This article proposes a multiview hashing with learnable parameters to retrieve the queried images for a large-scale remote sensing dataset. Existing methods always neglect that real-world remote sensing data lies on a low-dimensional manifold embedded in high-dimensional ambient space. Unlike previous methods, this article proposes to learn the consensus compact codes in a view-specific low-dimensional subspace. Furthermore, we have added a hyperparameter learnable module to avoid complex parameter tuning. In order to prove the effectiveness of our method, we carried out experiments on three widely used remote sensing data sets and compared them with seven state-of-the-art methods. Extensive experiments show that the proposed method can achieve competitive results compared to the other method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.04368v1-abstract-full').style.display = 'none'; document.getElementById('2304.04368v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 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,icassp accepted</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.10883">arXiv:2303.10883</a> <span> [<a href="https://arxiv.org/pdf/2303.10883">pdf</a>, <a href="https://arxiv.org/format/2303.10883">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"> Explicit Visual Prompting for Low-Level Structure Segmentations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weihuang Liu</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+X">Xi Shen</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.10883v2-abstract-short" style="display: inline;"> We consider the generic problem of detecting low-level structures in images, which includes segmenting the manipulated parts, identifying out-of-focus pixels, separating shadow regions, and detecting concealed objects. Whereas each such topic has been typically addressed with a domain-specific solution, we show that a unified approach performs well across all of them. We take inspiration from the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.10883v2-abstract-full').style.display = 'inline'; document.getElementById('2303.10883v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.10883v2-abstract-full" style="display: none;"> We consider the generic problem of detecting low-level structures in images, which includes segmenting the manipulated parts, identifying out-of-focus pixels, separating shadow regions, and detecting concealed objects. Whereas each such topic has been typically addressed with a domain-specific solution, we show that a unified approach performs well across all of them. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and the input's high-frequency components. The proposed EVP significantly outperforms other parameter-efficient tuning protocols under the same amount of tunable parameters (5.7% extra trainable parameters of each task). EVP also achieves state-of-the-art performances on diverse low-level structure segmentation tasks compared to task-specific solutions. Our code is available at: https://github.com/NiFangBaAGe/Explicit-Visual-Prompt. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.10883v2-abstract-full').style.display = 'none'; document.getElementById('2303.10883v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by CVPR 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.08524">arXiv:2303.08524</a> <span> [<a href="https://arxiv.org/pdf/2303.08524">pdf</a>, <a href="https://arxiv.org/format/2303.08524">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"> CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+W">Weihuang Liu</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+M">Menghan Xia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yong Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jue Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.08524v1-abstract-short" style="display: inline;"> Image inpainting aims to fill the missing hole of the input. It is hard to solve this task efficiently when facing high-resolution images due to two reasons: (1) Large reception field needs to be handled for high-resolution image inpainting. (2) The general encoder and decoder network synthesizes many background pixels synchronously due to the form of the image matrix. In this paper, we try to bre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.08524v1-abstract-full').style.display = 'inline'; document.getElementById('2303.08524v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.08524v1-abstract-full" style="display: none;"> Image inpainting aims to fill the missing hole of the input. It is hard to solve this task efficiently when facing high-resolution images due to two reasons: (1) Large reception field needs to be handled for high-resolution image inpainting. (2) The general encoder and decoder network synthesizes many background pixels synchronously due to the form of the image matrix. In this paper, we try to break the above limitations for the first time thanks to the recent development of continuous implicit representation. In detail, we down-sample and encode the degraded image to produce the spatial-adaptive parameters for each spatial patch via an attentional Fast Fourier Convolution(FFC)-based parameter generation network. Then, we take these parameters as the weights and biases of a series of multi-layer perceptron(MLP), where the input is the encoded continuous coordinates and the output is the synthesized color value. Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing. Then, the continuous position encoding will be helpful to synthesize the photo-realistic high-frequency textures by re-sampling the coordinate in a higher resolution. Also, our framework enables us to query the coordinates of missing pixels only in parallel, yielding a more efficient solution than the previous methods. Experiments show that the proposed method achieves real-time performance on the 2048$\times$2048 images using a single GTX 2080 Ti GPU and can handle 4096$\times$4096 images, with much better performance than existing state-of-the-art methods visually and numerically. The code is available at: https://github.com/NiFangBaAGe/CoordFill. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.08524v1-abstract-full').style.display = 'none'; document.getElementById('2303.08524v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by AAAI 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.06410">arXiv:2303.06410</a> <span> [<a href="https://arxiv.org/pdf/2303.06410">pdf</a>, <a href="https://arxiv.org/format/2303.06410">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <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"> Brain Diffuser: An End-to-End Brain Image to Brain Network Pipeline </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+B">Baiying Lei</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.06410v1-abstract-short" style="display: inline;"> Brain network analysis is essential for diagnosing and intervention for Alzheimer's disease (AD). However, previous research relied primarily on specific time-consuming and subjective toolkits. Only few tools can obtain the structural brain networks from brain diffusion tensor images (DTI). In this paper, we propose a diffusion based end-to-end brain network generative model Brain Diffuser that di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06410v1-abstract-full').style.display = 'inline'; document.getElementById('2303.06410v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.06410v1-abstract-full" style="display: none;"> Brain network analysis is essential for diagnosing and intervention for Alzheimer's disease (AD). However, previous research relied primarily on specific time-consuming and subjective toolkits. Only few tools can obtain the structural brain networks from brain diffusion tensor images (DTI). In this paper, we propose a diffusion based end-to-end brain network generative model Brain Diffuser that directly shapes the structural brain networks from DTI. Compared to existing toolkits, Brain Diffuser exploits more structural connectivity features and disease-related information by analyzing disparities in structural brain networks across subjects. For the case of Alzheimer's disease, the proposed model performs better than the results from existing toolkits on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06410v1-abstract-full').style.display = 'none'; document.getElementById('2303.06410v1-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.03837">arXiv:2302.03837</a> <span> [<a href="https://arxiv.org/pdf/2302.03837">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> </div> <p class="title is-5 mathjax"> Robust Digital Watermarking Method Based on Adaptive Feature Area Extraction and Local Histogram Shifting </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jiang%2C+Z">Zi-yu Jiang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Yuan%2C+X">Xiao-Chen Yuan</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tong Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2302.03837v1-abstract-short" style="display: inline;"> A new local watermarking method based on histogram shifting has been proposed in this paper to deal with various signal processing attacks (e.g. median filtering, JPEG compression and Gaussian noise addition) and geometric attacks (e.g. rotation, scaling and cropping). A feature detector is used to select local areas for embedding. Then stationary wavelet transform (SWT) is applied on each local a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03837v1-abstract-full').style.display = 'inline'; document.getElementById('2302.03837v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.03837v1-abstract-full" style="display: none;"> A new local watermarking method based on histogram shifting has been proposed in this paper to deal with various signal processing attacks (e.g. median filtering, JPEG compression and Gaussian noise addition) and geometric attacks (e.g. rotation, scaling and cropping). A feature detector is used to select local areas for embedding. Then stationary wavelet transform (SWT) is applied on each local area for denoising by setting the corresponding diagonal coefficients to zero. With the implementation of histogram shifting, the watermark is embedded into denoised local areas. Meanwhile, a secret key is used in the embedding process which ensures the security that the watermark cannot be easily hacked. After the embedding process, the SWT diagonal coefficients are used to reconstruct the watermarked image. With the proposed watermarking method, we can achieve higher image quality and less bit error rate (BER) in the decoding process even after some attacks. Compared with global watermarking methods, the proposed watermarking scheme based on local histogram shifting has the advantages of higher security and larger capacity. The experimental results show the better image quality as well as lower BER compared with the state-of-art watermarking methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.03837v1-abstract-full').style.display = 'none'; document.getElementById('2302.03837v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.08880">arXiv:2301.08880</a> <span> [<a href="https://arxiv.org/pdf/2301.08880">pdf</a>, <a href="https://arxiv.org/format/2301.08880">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"> A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zinuo Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.08880v3-abstract-short" style="display: inline;"> Film, a classic image style, is culturally significant to the whole photographic industry since it marks the birth of photography. However, film photography is time-consuming and expensive, necessitating a more efficient method for collecting film-style photographs. Numerous datasets that have emerged in the field of image enhancement so far are not film-specific. In order to facilitate film-based… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.08880v3-abstract-full').style.display = 'inline'; document.getElementById('2301.08880v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.08880v3-abstract-full" style="display: none;"> Film, a classic image style, is culturally significant to the whole photographic industry since it marks the birth of photography. However, film photography is time-consuming and expensive, necessitating a more efficient method for collecting film-style photographs. Numerous datasets that have emerged in the field of image enhancement so far are not film-specific. In order to facilitate film-based image stylization research, we construct FilmSet, a large-scale and high-quality film style dataset. Our dataset includes three different film types and more than 5000 in-the-wild high resolution images. Inspired by the features of FilmSet images, we propose a novel framework called FilmNet based on Laplacian Pyramid for stylizing images across frequency bands and achieving film style outcomes. Experiments reveal that the performance of our model is superior than state-of-the-art techniques. The link of code and data is \url{https://github.com/CXH-Research/FilmNet}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.08880v3-abstract-full').style.display = 'none'; document.getElementById('2301.08880v3-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by International Joint Conference on Artificial Intelligence (IJCAI 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/2212.08327">arXiv:2212.08327</a> <span> [<a href="https://arxiv.org/pdf/2212.08327">pdf</a>, <a href="https://arxiv.org/format/2212.08327">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+Z">Zinuo Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</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="2212.08327v2-abstract-short" style="display: inline;"> Image enhancement is a technique that frequently utilized in digital image processing. In recent years, the popularity of learning-based techniques for enhancing the aesthetic performance of photographs has increased. However, the majority of current works do not optimize an image from different frequency domains and typically focus on either pixel-level or global-level enhancements. In this paper… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.08327v2-abstract-full').style.display = 'inline'; document.getElementById('2212.08327v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.08327v2-abstract-full" style="display: none;"> Image enhancement is a technique that frequently utilized in digital image processing. In recent years, the popularity of learning-based techniques for enhancing the aesthetic performance of photographs has increased. However, the majority of current works do not optimize an image from different frequency domains and typically focus on either pixel-level or global-level enhancements. In this paper, we propose a transformer-based model in the wavelet domain to refine different frequency bands of an image. Our method focuses both on local details and high-level features for enhancement, which can generate superior results. On the basis of comprehensive benchmark evaluations, our method outperforms the state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.08327v2-abstract-full').style.display = 'none'; document.getElementById('2212.08327v2-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.16675">arXiv:2211.16675</a> <span> [<a href="https://arxiv.org/pdf/2211.16675">pdf</a>, <a href="https://arxiv.org/format/2211.16675">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/ICASSP49357.2023.10095403">10.1109/ICASSP49357.2023.10095403 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuqiang Wang</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="2211.16675v2-abstract-short" style="display: inline;"> Shadow removal improves the visual quality and legibility of digital copies of documents. However, document shadow removal remains an unresolved subject. Traditional techniques rely on heuristics that vary from situation to situation. Given the quality and quantity of current public datasets, the majority of neural network models are ill-equipped for this task. In this paper, we propose a Transfor… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.16675v2-abstract-full').style.display = 'inline'; document.getElementById('2211.16675v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.16675v2-abstract-full" style="display: none;"> Shadow removal improves the visual quality and legibility of digital copies of documents. However, document shadow removal remains an unresolved subject. Traditional techniques rely on heuristics that vary from situation to situation. Given the quality and quantity of current public datasets, the majority of neural network models are ill-equipped for this task. In this paper, we propose a Transformer-based model for document shadow removal that utilizes shadow context encoding and decoding in both shadow and shadow-free regions. Additionally, shadow detection and pixel-level enhancement are included in the whole coarse-to-fine process. On the basis of comprehensive benchmark evaluations, it is competitive with state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.16675v2-abstract-full').style.display = 'none'; document.getElementById('2211.16675v2-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.12650">arXiv:2207.12650</a> <span> [<a href="https://arxiv.org/pdf/2207.12650">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Asymmetric Scalable Cross-modal Hashing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenyun Li</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2207.12650v1-abstract-short" style="display: inline;"> Cross-modal hashing is a successful method to solve large-scale multimedia retrieval issue. A lot of matrix factorization-based hashing methods are proposed. However, the existing methods still struggle with a few problems, such as how to generate the binary codes efficiently rather than directly relax them to continuity. In addition, most of the existing methods choose to use an $n\times n$ simil… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.12650v1-abstract-full').style.display = 'inline'; document.getElementById('2207.12650v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.12650v1-abstract-full" style="display: none;"> Cross-modal hashing is a successful method to solve large-scale multimedia retrieval issue. A lot of matrix factorization-based hashing methods are proposed. However, the existing methods still struggle with a few problems, such as how to generate the binary codes efficiently rather than directly relax them to continuity. In addition, most of the existing methods choose to use an $n\times n$ similarity matrix for optimization, which makes the memory and computation unaffordable. In this paper we propose a novel Asymmetric Scalable Cross-Modal Hashing (ASCMH) to address these issues. It firstly introduces a collective matrix factorization to learn a common latent space from the kernelized features of different modalities, and then transforms the similarity matrix optimization to a distance-distance difference problem minimization with the help of semantic labels and common latent space. Hence, the computational complexity of the $n\times n$ asymmetric optimization is relieved. In the generation of hash codes we also employ an orthogonal constraint of label information, which is indispensable for search accuracy. So the redundancy of computation can be much reduced. For efficient optimization and scalable to large-scale datasets, we adopt the two-step approach rather than optimizing simultaneously. Extensive experiments on three benchmark datasets: Wiki, MIRFlickr-25K, and NUS-WIDE, demonstrate that our ASCMH outperforms the state-of-the-art cross-modal hashing methods in terms of accuracy and efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.12650v1-abstract-full').style.display = 'none'; document.getElementById('2207.12650v1-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 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.11438">arXiv:2207.11438</a> <span> [<a href="https://arxiv.org/pdf/2207.11438">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Arbitrary Style Transfer with Structure Enhancement by Combining the Global and Local Loss </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Long%2C+L">Lizhen Long</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2207.11438v1-abstract-short" style="display: inline;"> Arbitrary style transfer generates an artistic image which combines the structure of a content image and the artistic style of the artwork by using only one trained network. The image representation used in this method contains content structure representation and the style patterns representation, which is usually the features representation of high-level in the pre-trained classification network… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.11438v1-abstract-full').style.display = 'inline'; document.getElementById('2207.11438v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.11438v1-abstract-full" style="display: none;"> Arbitrary style transfer generates an artistic image which combines the structure of a content image and the artistic style of the artwork by using only one trained network. The image representation used in this method contains content structure representation and the style patterns representation, which is usually the features representation of high-level in the pre-trained classification networks. However, the traditional classification networks were designed for classification which usually focus on high-level features and ignore other features. As the result, the stylized images distribute style elements evenly throughout the image and make the overall image structure unrecognizable. To solve this problem, we introduce a novel arbitrary style transfer method with structure enhancement by combining the global and local loss. The local structure details are represented by Lapstyle and the global structure is controlled by the image depth. Experimental results demonstrate that our method can generate higher-quality images with impressive visual effects on several common datasets, comparing with other state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.11438v1-abstract-full').style.display = 'none'; document.getElementById('2207.11438v1-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 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.14058">arXiv:2205.14058</a> <span> [<a href="https://arxiv.org/pdf/2205.14058">pdf</a>, <a href="https://arxiv.org/format/2205.14058">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"> Image Harmonization with Region-wise Contrastive Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liang%2C+J">Jingtang Liang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2205.14058v2-abstract-short" style="display: inline;"> Image harmonization task aims at harmonizing different composite foreground regions according to specific background image. Previous methods would rather focus on improving the reconstruction ability of the generator by some internal enhancements such as attention, adaptive normalization and light adjustment, $etc.$. However, they pay less attention to discriminating the foreground and background… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.14058v2-abstract-full').style.display = 'inline'; document.getElementById('2205.14058v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.14058v2-abstract-full" style="display: none;"> Image harmonization task aims at harmonizing different composite foreground regions according to specific background image. Previous methods would rather focus on improving the reconstruction ability of the generator by some internal enhancements such as attention, adaptive normalization and light adjustment, $etc.$. However, they pay less attention to discriminating the foreground and background appearance features within a restricted generator, which becomes a new challenge in image harmonization task. In this paper, we propose a novel image harmonization framework with external style fusion and region-wise contrastive learning scheme. For the external style fusion, we leverage the external background appearance from the encoder as the style reference to generate harmonized foreground in the decoder. This approach enhances the harmonization ability of the decoder by external background guidance. Moreover, for the contrastive learning scheme, we design a region-wise contrastive loss function for image harmonization task. Specifically, we first introduce a straight-forward samples generation method that selects negative samples from the output harmonized foreground region and selects positive samples from the ground-truth background region. Our method attempts to bring together corresponding positive and negative samples by maximizing the mutual information between the foreground and background styles, which desirably makes our harmonization network more robust to discriminate the foreground and background style features when harmonizing composite images. Extensive experiments on the benchmark datasets show that our method can achieve a clear improvement in harmonization quality and demonstrate the good generalization capability in real-scenario applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.14058v2-abstract-full').style.display = 'none'; document.getElementById('2205.14058v2-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 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2203.11068">arXiv:2203.11068</a> <span> [<a href="https://arxiv.org/pdf/2203.11068">pdf</a>, <a href="https://arxiv.org/format/2203.11068">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 Enriched Illuminants for Cross and Single Sensor Color Constancy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cun%2C+X">Xiaodong Cun</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zhendong Wang</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jianzhuang Liu</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+W">Wengang Zhou</a>, <a href="/search/cs?searchtype=author&query=Jia%2C+X">Xu Jia</a>, <a href="/search/cs?searchtype=author&query=Li%2C+H">Houqiang Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2203.11068v1-abstract-short" style="display: inline;"> Color constancy aims to restore the constant colors of a scene under different illuminants. However, due to the existence of camera spectral sensitivity, the network trained on a certain sensor, cannot work well on others. Also, since the training datasets are collected in certain environments, the diversity of illuminants is limited for complex real world prediction. In this paper, we tackle thes… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.11068v1-abstract-full').style.display = 'inline'; document.getElementById('2203.11068v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2203.11068v1-abstract-full" style="display: none;"> Color constancy aims to restore the constant colors of a scene under different illuminants. However, due to the existence of camera spectral sensitivity, the network trained on a certain sensor, cannot work well on others. Also, since the training datasets are collected in certain environments, the diversity of illuminants is limited for complex real world prediction. In this paper, we tackle these problems via two aspects. First, we propose cross-sensor self-supervised training to train the network. In detail, we consider both the general sRGB images and the white-balanced RAW images from current available datasets as the white-balanced agents. Then, we train the network by randomly sampling the artificial illuminants in a sensor-independent manner for scene relighting and supervision. Second, we analyze a previous cascaded framework and present a more compact and accurate model by sharing the backbone parameters with learning attention specifically. Experiments show that our cross-sensor model and single-sensor model outperform other state-of-the-art methods by a large margin on cross and single sensor evaluations, respectively, with only 16% parameters of the previous best model. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2203.11068v1-abstract-full').style.display = 'none'; document.getElementById('2203.11068v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 March, 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">Tech report</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2201.08126">arXiv:2201.08126</a> <span> [<a href="https://arxiv.org/pdf/2201.08126">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Reversible Data Hiding in Encrypted Images by Lossless Pixel Conversion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+Z">Zi-Long Liu</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2201.08126v1-abstract-short" style="display: inline;"> Reversible data hiding in encrypted image (RDHEI) becomes a hot topic, and a lot of algorithms have been proposed to optimize this technology. However, these algorithms cannot achieve strong embedding capacity. Thus, in this paper, we propose an advanced RDHEI scheme based on lossless pixel conversion (LPC). Different from the previous RDHEI algorithms, LPC is inspired by the planar map coloring q… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.08126v1-abstract-full').style.display = 'inline'; document.getElementById('2201.08126v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2201.08126v1-abstract-full" style="display: none;"> Reversible data hiding in encrypted image (RDHEI) becomes a hot topic, and a lot of algorithms have been proposed to optimize this technology. However, these algorithms cannot achieve strong embedding capacity. Thus, in this paper, we propose an advanced RDHEI scheme based on lossless pixel conversion (LPC). Different from the previous RDHEI algorithms, LPC is inspired by the planar map coloring question, and it performs a dynamic image division process to divide the original image into irregular regions instead of regular blocks as in the previous RDHEI algorithms. In the process of LPC, pixel conversion is performed by region; that is, pixels in the same regions are converted to the same conversion values, which will occupy a smaller size, and then the available room can be reserved to accommodate additional data. LPC is a reversible process, so the original image can be losslessly recovered on the receiver side. Experimental results show that the embedding capacity of the proposed scheme outperforms the existing RDHEI algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2201.08126v1-abstract-full').style.display = 'none'; document.getElementById('2201.08126v1-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 January, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE TDSC</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.12070">arXiv:2112.12070</a> <span> [<a href="https://arxiv.org/pdf/2112.12070">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> A Single-Target License Plate Detection with Attention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+W">Wenyun Li</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C">Chi-Man Pun</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="2112.12070v1-abstract-short" style="display: inline;"> With the development of deep learning, Neural Network is commonly adopted to the License Plate Detection (LPD) task and achieves much better performance and precision, especially CNN-based networks can achieve state of the art RetinaNet[1]. For a single object detection task such as LPD, modified general object detection would be time-consuming, unable to cope with complex scenarios and a cumberso… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.12070v1-abstract-full').style.display = 'inline'; document.getElementById('2112.12070v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.12070v1-abstract-full" style="display: none;"> With the development of deep learning, Neural Network is commonly adopted to the License Plate Detection (LPD) task and achieves much better performance and precision, especially CNN-based networks can achieve state of the art RetinaNet[1]. For a single object detection task such as LPD, modified general object detection would be time-consuming, unable to cope with complex scenarios and a cumbersome weights file that is too hard to deploy on the embedded device. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.12070v1-abstract-full').style.display = 'none'; document.getElementById('2112.12070v1-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">IWAIT2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.14295">arXiv:2110.14295</a> <span> [<a href="https://arxiv.org/pdf/2110.14295">pdf</a>, <a href="https://arxiv.org/format/2110.14295">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> A Subgame Perfect Equilibrium Reinforcement Learning Approach to Time-inconsistent Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lesmana%2C+N+S">Nixie S. Lesmana</a>, <a href="/search/cs?searchtype=author&query=Pun%2C+C+S">Chi Seng Pun</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="2110.14295v1-abstract-short" style="display: inline;"> In this paper, we establish a subgame perfect equilibrium reinforcement learning (SPERL) framework for time-inconsistent (TIC) problems. In the context of RL, TIC problems are known to face two main challenges: the non-existence of natural recursive relationships between value functions at different time points and the violation of Bellman's principle of optimality that raises questions on the app… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.14295v1-abstract-full').style.display = 'inline'; document.getElementById('2110.14295v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.14295v1-abstract-full" style="display: none;"> In this paper, we establish a subgame perfect equilibrium reinforcement learning (SPERL) framework for time-inconsistent (TIC) problems. In the context of RL, TIC problems are known to face two main challenges: the non-existence of natural recursive relationships between value functions at different time points and the violation of Bellman's principle of optimality that raises questions on the applicability of standard policy iteration algorithms for unprovable policy improvement theorems. We adapt an extended dynamic programming theory and propose a new class of algorithms, called backward policy iteration (BPI), that solves SPERL and addresses both challenges. To demonstrate the practical usage of BPI as a training framework, we adapt standard RL simulation methods and derive two BPI-based training algorithms. We examine our derived training frameworks on a mean-variance portfolio selection problem and evaluate some performance metrics including convergence and model identifiability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.14295v1-abstract-full').style.display = 'none'; document.getElementById('2110.14295v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </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=Pun%2C+C&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Pun%2C+C&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Pun%2C+C&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