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 1–18 of 18 results for author: <span class="mathjax">Che, 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=Che%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="Che, 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=Che%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="Che, 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> <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/2411.13949">arXiv:2411.13949</a> <span> [<a href="https://arxiv.org/pdf/2411.13949">pdf</a>, <a href="https://arxiv.org/format/2411.13949">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"> Separable Mixture of Low-Rank Adaptation for Continual Visual Instruction Tuning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Ziqi Wang</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Q">Qi Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yangyang Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+Z">Zenglin Shi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+M">Meng 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="2411.13949v1-abstract-short" style="display: inline;"> Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT) extends the capability of MLLMs to incrementally learn new tasks, accommodating evolving functionalities. While prior work has advanced CVIT through the develo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13949v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13949v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13949v1-abstract-full" style="display: none;"> Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT) extends the capability of MLLMs to incrementally learn new tasks, accommodating evolving functionalities. While prior work has advanced CVIT through the development of new benchmarks and approaches to mitigate catastrophic forgetting, these efforts largely follow traditional continual learning paradigms, neglecting the unique challenges specific to CVIT. We identify a dual form of catastrophic forgetting in CVIT, where MLLMs not only forget previously learned visual understanding but also experience a decline in instruction following abilities as they acquire new tasks. To address this, we introduce the Separable Mixture of Low-Rank Adaptation (SMoLoRA) framework, which employs separable routing through two distinct modules - one for visual understanding and another for instruction following. This dual-routing design enables specialized adaptation in both domains, preventing forgetting while improving performance. Furthermore, we propose a novel CVIT benchmark that goes beyond existing benchmarks by additionally evaluating a model's ability to generalize to unseen tasks and handle diverse instructions across various tasks. Extensive experiments demonstrate that SMoLoRA outperforms existing methods in mitigating dual forgetting, improving generalization to unseen tasks, and ensuring robustness in following diverse instructions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13949v1-abstract-full').style.display = 'none'; document.getElementById('2411.13949v1-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 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/2410.18983">arXiv:2410.18983</a> <span> [<a href="https://arxiv.org/pdf/2410.18983">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Smart Navigation System for Parking Assignment at Large Events: Incorporating Heterogeneous Driver Characteristics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cheng%2C+X">Xi Cheng</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+T">Tong Liu</a>, <a href="/search/cs?searchtype=author&query=Su%2C+G">Gaofeng Su</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+C">Chen Zhu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+K">Ke Liu</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+B">Binze Cai</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+X">Xin Hu</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="2410.18983v1-abstract-short" style="display: inline;"> Parking challenges escalate significantly during large events such as concerts and sports games, yet few studies address dynamic parking lot assignments in these occasions. This paper introduces a smart navigation system designed to optimize parking assignments efficiently during major events, employing a mixed search algorithm that considers diverse drivers characteristics. We validated our syste… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18983v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18983v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18983v1-abstract-full" style="display: none;"> Parking challenges escalate significantly during large events such as concerts and sports games, yet few studies address dynamic parking lot assignments in these occasions. This paper introduces a smart navigation system designed to optimize parking assignments efficiently during major events, employing a mixed search algorithm that considers diverse drivers characteristics. We validated our system through simulations conducted in Berkeley, CA during the "Big Game" showcasing the advantages of our novel parking assignment approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18983v1-abstract-full').style.display = 'none'; document.getElementById('2410.18983v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 October, 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">arXiv admin note: text overlap with arXiv:2406.05135</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.16924">arXiv:2408.16924</a> <span> [<a href="https://arxiv.org/pdf/2408.16924">pdf</a>, <a href="https://arxiv.org/format/2408.16924">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="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Autism Spectrum Disorder Early Detection with the Parent-Child Dyads Block-Play Protocol and an Attention-enhanced GCN-xLSTM Hybrid Deep Learning Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+L">Lizhou Fan</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+H">Hanbo Wu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+K">Kunping Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+X">Xiaoxiao Yu</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chao Che</a>, <a href="/search/cs?searchtype=author&query=Cai%2C+Z">Zhifeng Cai</a>, <a href="/search/cs?searchtype=author&query=Niu%2C+X">Xiuhong Niu</a>, <a href="/search/cs?searchtype=author&query=Cao%2C+A">Aihua Cao</a>, <a href="/search/cs?searchtype=author&query=Ma%2C+X">Xin Ma</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="2408.16924v1-abstract-short" style="display: inline;"> Autism Spectrum Disorder (ASD) is a rapidly growing neurodevelopmental disorder. Performing a timely intervention is crucial for the growth of young children with ASD, but traditional clinical screening methods lack objectivity. This study introduces an innovative approach to early detection of ASD. The contributions are threefold. First, this work proposes a novel Parent-Child Dyads Block-Play (P… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16924v1-abstract-full').style.display = 'inline'; document.getElementById('2408.16924v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.16924v1-abstract-full" style="display: none;"> Autism Spectrum Disorder (ASD) is a rapidly growing neurodevelopmental disorder. Performing a timely intervention is crucial for the growth of young children with ASD, but traditional clinical screening methods lack objectivity. This study introduces an innovative approach to early detection of ASD. The contributions are threefold. First, this work proposes a novel Parent-Child Dyads Block-Play (PCB) protocol, grounded in kinesiological and neuroscientific research, to identify behavioral patterns distinguishing ASD from typically developing (TD) toddlers. Second, we have compiled a substantial video dataset, featuring 40 ASD and 89 TD toddlers engaged in block play with parents. This dataset exceeds previous efforts on both the scale of participants and the length of individual sessions. Third, our approach to action analysis in videos employs a hybrid deep learning framework, integrating a two-stream graph convolution network with attention-enhanced xLSTM (2sGCN-AxLSTM). This framework is adept at capturing dynamic interactions between toddlers and parents by extracting spatial features correlated with upper body and head movements and focusing on global contextual information of action sequences over time. By learning these global features with spatio-temporal correlations, our 2sGCN-AxLSTM effectively analyzes dynamic human behavior patterns and demonstrates an unprecedented accuracy of 89.6\% in early detection of ASD. Our approach shows strong potential for enhancing early ASD diagnosis by accurately analyzing parent-child interactions, providing a critical tool to support timely and informed clinical decision-making. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16924v1-abstract-full').style.display = 'none'; document.getElementById('2408.16924v1-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 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">18 pages, 8 figures, and 4 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.16295">arXiv:2407.16295</a> <span> [<a href="https://arxiv.org/pdf/2407.16295">pdf</a>, <a href="https://arxiv.org/format/2407.16295">other</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"> Manifoldchain: Maximizing Blockchain Throughput via Bandwidth-Clustered Sharding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Che%2C+C">Chunjiang Che</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Songze Li</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+X">Xuechao 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="2407.16295v1-abstract-short" style="display: inline;"> Bandwidth limitation is the major bottleneck that hinders scaling throughput of proof-of-work blockchains. To guarantee security, the mining rate of the blockchain is determined by the miners with the lowest bandwidth, resulting in an inefficient bandwidth utilization among fast miners. We propose Manifoldchain, an innovative blockchain sharding protocol that alleviates the impact of slow miners t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16295v1-abstract-full').style.display = 'inline'; document.getElementById('2407.16295v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.16295v1-abstract-full" style="display: none;"> Bandwidth limitation is the major bottleneck that hinders scaling throughput of proof-of-work blockchains. To guarantee security, the mining rate of the blockchain is determined by the miners with the lowest bandwidth, resulting in an inefficient bandwidth utilization among fast miners. We propose Manifoldchain, an innovative blockchain sharding protocol that alleviates the impact of slow miners to maximize blockchain throughput. Manifoldchain utilizes a bandwidth-clustered shard formation mechanism that groups miners with similar bandwidths into the same shard. Consequently, this approach enables us to set an optimal mining rate for each shard based on its bandwidth, effectively reducing the waiting time caused by slow miners. Nevertheless, the adversary could corrupt miners with similar bandwidths, thereby concentrating hashing power and potentially creating an adversarial majority within a single shard. To counter this adversarial strategy, we introduce sharing mining, allowing the honest mining power of the entire network to participate in the secure ledger formation of each shard, thereby achieving the same level of security as an unsharded blockchain. Additionally, we introduce an asynchronous atomic commitment mechanism to ensure transaction atomicity across shards with various mining rates. Our theoretical analysis demonstrates that Manifoldchain scales linearly in throughput with the increase in shard numbers and inversely with network delay in each shard. We implement a full system prototype of Manifoldchain, comprehensively evaluated on both simulated and real-world testbeds. These experiments validate its vertical scalability with network bandwidth and horizontal scalability with network size, achieving a substantial improvement of 186% in throughput over baseline sharding protocols, for scenarios where bandwidths of miners range from 5Mbps to 60Mbps. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16295v1-abstract-full').style.display = 'none'; document.getElementById('2407.16295v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.00362">arXiv:2407.00362</a> <span> [<a href="https://arxiv.org/pdf/2407.00362">pdf</a>, <a href="https://arxiv.org/format/2407.00362">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"> JSCDS: A Core Data Selection Method with Jason-Shannon Divergence for Caries RGB Images-Efficient Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+P">Peiliang Zhang</a>, <a href="/search/cs?searchtype=author&query=Tong%2C+Y">Yujia Tong</a>, <a href="/search/cs?searchtype=author&query=Du%2C+C">Chenghu Du</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chao Che</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yongjun Zhu</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="2407.00362v2-abstract-short" style="display: inline;"> Deep learning-based RGB caries detection improves the efficiency of caries identification and is crucial for preventing oral diseases. The performance of deep learning models depends on high-quality data and requires substantial training resources, making efficient deployment challenging. Core data selection, by eliminating low-quality and confusing data, aims to enhance training efficiency withou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00362v2-abstract-full').style.display = 'inline'; document.getElementById('2407.00362v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.00362v2-abstract-full" style="display: none;"> Deep learning-based RGB caries detection improves the efficiency of caries identification and is crucial for preventing oral diseases. The performance of deep learning models depends on high-quality data and requires substantial training resources, making efficient deployment challenging. Core data selection, by eliminating low-quality and confusing data, aims to enhance training efficiency without significantly compromising model performance. However, distance-based data selection methods struggle to distinguish dependencies among high-dimensional caries data. To address this issue, we propose a Core Data Selection Method with Jensen-Shannon Divergence (JSCDS) for efficient caries image learning and caries classification. We describe the core data selection criterion as the distribution of samples in different classes. JSCDS calculates the cluster centers by sample embedding representation in the caries classification network and utilizes Jensen-Shannon Divergence to compute the mutual information between data samples and cluster centers, capturing nonlinear dependencies among high-dimensional data. The average mutual information is calculated to fit the above distribution, serving as the criterion for constructing the core set for model training. Extensive experiments on RGB caries datasets show that JSCDS outperforms other data selection methods in prediction performance and time consumption. Notably, JSCDS exceeds the performance of the full dataset model with only 50% of the core data, with its performance advantage becoming more pronounced in the 70% of core data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.00362v2-abstract-full').style.display = 'none'; document.getElementById('2407.00362v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 June, 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 in KDD 2024 Workshop AIDSH</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.10744">arXiv:2406.10744</a> <span> [<a href="https://arxiv.org/pdf/2406.10744">pdf</a>, <a href="https://arxiv.org/format/2406.10744">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"> Technique Report of CVPR 2024 PBDL Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fu%2C+Y">Ying Fu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yu Li</a>, <a href="/search/cs?searchtype=author&query=You%2C+S">Shaodi You</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+B">Boxin Shi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+L">Linwei Chen</a>, <a href="/search/cs?searchtype=author&query=Zou%2C+Y">Yunhao Zou</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zichun Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+Y">Yichen Li</a>, <a href="/search/cs?searchtype=author&query=Han%2C+Y">Yuze Han</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yingkai Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+J">Jianan Wang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+Q">Qinglin Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+W">Wei Yu</a>, <a href="/search/cs?searchtype=author&query=Lv%2C+X">Xiaoqian Lv</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jianing Li</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+S">Shengping Zhang</a>, <a href="/search/cs?searchtype=author&query=Ji%2C+X">Xiangyang Ji</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+Y">Yuanpei Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Y">Yuhan Zhang</a>, <a href="/search/cs?searchtype=author&query=Peng%2C+W">Weihang Peng</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+L">Liwen Zhang</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+Z">Zhe Xu</a>, <a href="/search/cs?searchtype=author&query=Gou%2C+D">Dingyong Gou</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Cong Li</a>, <a href="/search/cs?searchtype=author&query=Xu%2C+S">Senyan Xu</a> , et al. (75 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.10744v3-abstract-short" style="display: inline;"> The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10744v3-abstract-full').style.display = 'inline'; document.getElementById('2406.10744v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10744v3-abstract-full" style="display: none;"> The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10744v3-abstract-full').style.display = 'none'; document.getElementById('2406.10744v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 July, 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">CVPR 2024 PBDL Challenges: https://pbdl-ws.github.io/pbdl2024/challenge/index.html</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.07479">arXiv:2405.07479</a> <span> [<a href="https://arxiv.org/pdf/2405.07479">pdf</a>, <a href="https://arxiv.org/format/2405.07479">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Enhancing 3D Object Detection by Using Neural Network with Self-adaptive Thresholding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+H">Houze Liu</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+C">Chongqing Wang</a>, <a href="/search/cs?searchtype=author&query=Zhan%2C+X">Xiaoan Zhan</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H">Haotian Zheng</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.07479v1-abstract-short" style="display: inline;"> Robust 3D object detection remains a pivotal concern in the domain of autonomous field robotics. Despite notable enhancements in detection accuracy across standard datasets, real-world urban environments, characterized by their unstructured and dynamic nature, frequently precipitate an elevated incidence of false positives, thereby undermining the reliability of existing detection paradigms. In th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.07479v1-abstract-full').style.display = 'inline'; document.getElementById('2405.07479v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.07479v1-abstract-full" style="display: none;"> Robust 3D object detection remains a pivotal concern in the domain of autonomous field robotics. Despite notable enhancements in detection accuracy across standard datasets, real-world urban environments, characterized by their unstructured and dynamic nature, frequently precipitate an elevated incidence of false positives, thereby undermining the reliability of existing detection paradigms. In this context, our study introduces an advanced post-processing algorithm that modulates detection thresholds dynamically relative to the distance from the ego object. Traditional perception systems typically utilize a uniform threshold, which often leads to decreased efficacy in detecting distant objects. In contrast, our proposed methodology employs a Neural Network with a self-adaptive thresholding mechanism that significantly attenuates false negatives while concurrently diminishing false positives, particularly in complex urban settings. Empirical results substantiate that our algorithm not only augments the performance of 3D object detection models in diverse urban and adverse weather scenarios but also establishes a new benchmark for adaptive thresholding techniques in field robotics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.07479v1-abstract-full').style.display = 'none'; document.getElementById('2405.07479v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been accepted by the CONF-SEML 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.03523">arXiv:2404.03523</a> <span> [<a href="https://arxiv.org/pdf/2404.03523">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> Integrating Generative AI into Financial Market Prediction for Improved Decision Making </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zengyi Huang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+C">Chen Li</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H">Haotian Zheng</a>, <a href="/search/cs?searchtype=author&query=Tian%2C+X">Xinyu Tian</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.03523v1-abstract-short" style="display: inline;"> This study provides an in-depth analysis of the model architecture and key technologies of generative artificial intelligence, combined with specific application cases, and uses conditional generative adversarial networks ( cGAN ) and time series analysis methods to simulate and predict dynamic changes in financial markets. The research results show that the cGAN model can effectively capture the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03523v1-abstract-full').style.display = 'inline'; document.getElementById('2404.03523v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.03523v1-abstract-full" style="display: none;"> This study provides an in-depth analysis of the model architecture and key technologies of generative artificial intelligence, combined with specific application cases, and uses conditional generative adversarial networks ( cGAN ) and time series analysis methods to simulate and predict dynamic changes in financial markets. The research results show that the cGAN model can effectively capture the complexity of financial market data, and the deviation between the prediction results and the actual market performance is minimal, showing a high degree of accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03523v1-abstract-full').style.display = 'none'; document.getElementById('2404.03523v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.01116">arXiv:2404.01116</a> <span> [<a href="https://arxiv.org/pdf/2404.01116">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Intelligent Robotic Control System Based on Computer Vision Technology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+H">Haotian Zheng</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zengyi Huang</a>, <a href="/search/cs?searchtype=author&query=Jiang%2C+W">Wei Jiang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo 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="2404.01116v1-abstract-short" style="display: inline;"> The article explores the intersection of computer vision technology and robotic control, highlighting its importance in various fields such as industrial automation, healthcare, and environmental protection. Computer vision technology, which simulates human visual observation, plays a crucial role in enabling robots to perceive and understand their surroundings, leading to advancements in tasks li… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01116v1-abstract-full').style.display = 'inline'; document.getElementById('2404.01116v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.01116v1-abstract-full" style="display: none;"> The article explores the intersection of computer vision technology and robotic control, highlighting its importance in various fields such as industrial automation, healthcare, and environmental protection. Computer vision technology, which simulates human visual observation, plays a crucial role in enabling robots to perceive and understand their surroundings, leading to advancements in tasks like autonomous navigation, object recognition, and waste management. By integrating computer vision with robot control, robots gain the ability to interact intelligently with their environment, improving efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01116v1-abstract-full').style.display = 'none'; document.getElementById('2404.01116v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.06782">arXiv:2401.06782</a> <span> [<a href="https://arxiv.org/pdf/2401.06782">pdf</a>, <a href="https://arxiv.org/format/2401.06782">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yu%2C+L">Liqiang Yu</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo Liu</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qunwei Lin</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xinyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</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="2401.06782v1-abstract-short" style="display: inline;"> In the realm of patent document analysis, assessing semantic similarity between phrases presents a significant challenge, notably amplifying the inherent complexities of Cooperative Patent Classification (CPC) research. Firstly, this study addresses these challenges, recognizing early CPC work while acknowledging past struggles with language barriers and document intricacy. Secondly, it underscore… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.06782v1-abstract-full').style.display = 'inline'; document.getElementById('2401.06782v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.06782v1-abstract-full" style="display: none;"> In the realm of patent document analysis, assessing semantic similarity between phrases presents a significant challenge, notably amplifying the inherent complexities of Cooperative Patent Classification (CPC) research. Firstly, this study addresses these challenges, recognizing early CPC work while acknowledging past struggles with language barriers and document intricacy. Secondly, it underscores the persisting difficulties of CPC research. To overcome these challenges and bolster the CPC system, This paper presents two key innovations. Firstly, it introduces an ensemble approach that incorporates four BERT-related models, enhancing semantic similarity accuracy through weighted averaging. Secondly, a novel text preprocessing method tailored for patent documents is introduced, featuring a distinctive input structure with token scoring that aids in capturing semantic relationships during CPC context training, utilizing BCELoss. Our experimental findings conclusively establish the effectiveness of both our Ensemble Model and novel text processing strategies when deployed on the U.S. Patent Phrase to Phrase Matching dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.06782v1-abstract-full').style.display = 'none'; document.getElementById('2401.06782v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">It accepted by The 6th International Conference on Machine Learning and Machine Intelligence (MLMI 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/2401.06167">arXiv:2401.06167</a> <span> [<a href="https://arxiv.org/pdf/2401.06167">pdf</a>, <a href="https://arxiv.org/format/2401.06167">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"> Enhancing Multimodal Understanding with CLIP-Based Image-to-Text Transformation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qunwei Lin</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xinyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiaxin Huang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Liqiang Yu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.06167v1-abstract-short" style="display: inline;"> The process of transforming input images into corresponding textual explanations stands as a crucial and complex endeavor within the domains of computer vision and natural language processing. In this paper, we propose an innovative ensemble approach that harnesses the capabilities of Contrastive Language-Image Pretraining models. </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.06167v1-abstract-full" style="display: none;"> The process of transforming input images into corresponding textual explanations stands as a crucial and complex endeavor within the domains of computer vision and natural language processing. In this paper, we propose an innovative ensemble approach that harnesses the capabilities of Contrastive Language-Image Pretraining models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.06167v1-abstract-full').style.display = 'none'; document.getElementById('2401.06167v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 January, 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/2401.05433">arXiv:2401.05433</a> <span> [<a href="https://arxiv.org/pdf/2401.05433">pdf</a>, <a href="https://arxiv.org/format/2401.05433">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Essay Scoring with Adversarial Weights Perturbation and Metric-specific AttentionPooling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+J">Jiaxin Huang</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xinyu Zhao</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qunwei Lin</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo 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="2401.05433v1-abstract-short" style="display: inline;"> The objective of this study is to improve automated feedback tools designed for English Language Learners (ELLs) through the utilization of data science techniques encompassing machine learning, natural language processing, and educational data analytics. Automated essay scoring (AES) research has made strides in evaluating written essays, but it often overlooks the specific needs of English Langu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05433v1-abstract-full').style.display = 'inline'; document.getElementById('2401.05433v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.05433v1-abstract-full" style="display: none;"> The objective of this study is to improve automated feedback tools designed for English Language Learners (ELLs) through the utilization of data science techniques encompassing machine learning, natural language processing, and educational data analytics. Automated essay scoring (AES) research has made strides in evaluating written essays, but it often overlooks the specific needs of English Language Learners (ELLs) in language development. This study explores the application of BERT-related techniques to enhance the assessment of ELLs' writing proficiency within AES. To address the specific needs of ELLs, we propose the use of DeBERTa, a state-of-the-art neural language model, for improving automated feedback tools. DeBERTa, pretrained on large text corpora using self-supervised learning, learns universal language representations adaptable to various natural language understanding tasks. The model incorporates several innovative techniques, including adversarial training through Adversarial Weights Perturbation (AWP) and Metric-specific AttentionPooling (6 kinds of AP) for each label in the competition. The primary focus of this research is to investigate the impact of hyperparameters, particularly the adversarial learning rate, on the performance of the model. By fine-tuning the hyperparameter tuning process, including the influence of 6AP and AWP, the resulting models can provide more accurate evaluations of language proficiency and support tailored learning tasks for ELLs. This work has the potential to significantly benefit ELLs by improving their English language proficiency and facilitating their educational journey. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05433v1-abstract-full').style.display = 'none'; document.getElementById('2401.05433v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This article was accepted by 2023 International Conference on Information Network and Computer Communications(INCC)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.12872">arXiv:2312.12872</a> <span> [<a href="https://arxiv.org/pdf/2312.12872">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Integration and Performance Analysis of Artificial Intelligence and Computer Vision Based on Deep Learning Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Liu%2C+B">Bo Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+L">Liqiang Yu</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chang Che</a>, <a href="/search/cs?searchtype=author&query=Lin%2C+Q">Qunwei Lin</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+H">Hao Hu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+X">Xinyu Zhao</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="2312.12872v1-abstract-short" style="display: inline;"> This paper focuses on the analysis of the application effectiveness of the integration of deep learning and computer vision technologies. Deep learning achieves a historic breakthrough by constructing hierarchical neural networks, enabling end-to-end feature learning and semantic understanding of images. The successful experiences in the field of computer vision provide strong support for training… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.12872v1-abstract-full').style.display = 'inline'; document.getElementById('2312.12872v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.12872v1-abstract-full" style="display: none;"> This paper focuses on the analysis of the application effectiveness of the integration of deep learning and computer vision technologies. Deep learning achieves a historic breakthrough by constructing hierarchical neural networks, enabling end-to-end feature learning and semantic understanding of images. The successful experiences in the field of computer vision provide strong support for training deep learning algorithms. The tight integration of these two fields has given rise to a new generation of advanced computer vision systems, significantly surpassing traditional methods in tasks such as machine vision image classification and object detection. In this paper, typical image classification cases are combined to analyze the superior performance of deep neural network models while also pointing out their limitations in generalization and interpretability, proposing directions for future improvements. Overall, the efficient integration and development trend of deep learning with massive visual data will continue to drive technological breakthroughs and application expansion in the field of computer vision, making it possible to build truly intelligent machine vision systems. This deepening fusion paradigm will powerfully promote unprecedented tasks and functions in computer vision, providing stronger development momentum for related disciplines and industries. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.12872v1-abstract-full').style.display = 'none'; document.getElementById('2312.12872v1-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">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/2301.05639">arXiv:2301.05639</a> <span> [<a href="https://arxiv.org/pdf/2301.05639">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Chemical Physics">physics.chem-ph</span> </div> </div> <p class="title is-5 mathjax"> Predictions of photophysical properties of phosphorescent platinum(II) complexes based on ensemble machine learning approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+S">Shuai Wang</a>, <a href="/search/cs?searchtype=author&query=Yam%2C+C">ChiYung Yam</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+S">Shuguang Chen</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+L">Lihong Hu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+L">Liping Li</a>, <a href="/search/cs?searchtype=author&query=Hung%2C+F">Faan-Fung Hung</a>, <a href="/search/cs?searchtype=author&query=Fan%2C+J">Jiaqi Fan</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chi-Ming Che</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+G">GuanHua Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2301.05639v1-abstract-short" style="display: inline;"> Phosphorescent metal complexes have been under intense investigations as emissive dopants for energy efficient organic light emitting diodes (OLEDs). Among them, cyclometalated Pt(II) complexes are widespread triplet emitters with color-tunable emissions. To render their practical applications as OLED emitters, it is in great need to develop Pt(II) complexes with high radiative decay rate constant… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.05639v1-abstract-full').style.display = 'inline'; document.getElementById('2301.05639v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.05639v1-abstract-full" style="display: none;"> Phosphorescent metal complexes have been under intense investigations as emissive dopants for energy efficient organic light emitting diodes (OLEDs). Among them, cyclometalated Pt(II) complexes are widespread triplet emitters with color-tunable emissions. To render their practical applications as OLED emitters, it is in great need to develop Pt(II) complexes with high radiative decay rate constant ($k_r$) and photoluminescence (PL) quantum yield. Thus, an efficient and accurate prediction tool is highly desirable. Here, we develop a general protocol for accurate predictions of emission wavelength, radiative decay rate constant, and PL quantum yield for phosphorescent Pt(II) emitters based on the combination of first-principles quantum mechanical method, machine learning (ML) and experimental calibration. A new dataset concerning phosphorescent Pt(II) emitters is constructed, with more than two hundred samples collected from the literature. Features containing pertinent electronic properties of the complexes are chosen. Our results demonstrate that ensemble learning models combined with stacking-based approaches exhibit the best performance, where the values of squared correlation coefficients ($R^2$), mean absolute error (MAE), and root mean square error (RMSE) are 0.96, 7.21 nm and 13.00 nm for emission wavelength prediction, and 0.81, 0.11 and 0.15 for PL quantum yield prediction. For radiative decay rate constant ($k_r$), the obtained value of $R^2$ is 0.67 while MAE and RMSE are 0.21 and 0.25 (both in log scale), respectively. The accuracy of the protocol is further confirmed using 24 recently reported Pt(II) complexes, which demonstrates its reliability for a broad palette of Pt(II) emitters.We expect this protocol will become a valuable tool, accelerating the rational design of novel OLED materials with desired properties. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.05639v1-abstract-full').style.display = 'none'; document.getElementById('2301.05639v1-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 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2108.00365">arXiv:2108.00365</a> <span> [<a href="https://arxiv.org/pdf/2108.00365">pdf</a>, <a href="https://arxiv.org/format/2108.00365">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="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/TPDS.2022.3202887">10.1109/TPDS.2022.3202887 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Che%2C+C">Chunjiang Che</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xiaoli Li</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chuan Chen</a>, <a href="/search/cs?searchtype=author&query=He%2C+X">Xiaoyu He</a>, <a href="/search/cs?searchtype=author&query=Zheng%2C+Z">Zibin Zheng</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2108.00365v2-abstract-short" style="display: inline;"> Federated learning allows multiple participants to collaboratively train an efficient model without exposing data privacy. However, this distributed machine learning training method is prone to attacks from Byzantine clients, which interfere with the training of the global model by modifying the model or uploading the false gradient. In this paper, we propose a novel serverless federated learning… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.00365v2-abstract-full').style.display = 'inline'; document.getElementById('2108.00365v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2108.00365v2-abstract-full" style="display: none;"> Federated learning allows multiple participants to collaboratively train an efficient model without exposing data privacy. However, this distributed machine learning training method is prone to attacks from Byzantine clients, which interfere with the training of the global model by modifying the model or uploading the false gradient. In this paper, we propose a novel serverless federated learning framework Committee Mechanism based Federated Learning (CMFL), which can ensure the robustness of the algorithm with convergence guarantee. In CMFL, a committee system is set up to screen the uploaded local gradients. The committee system selects the local gradients rated by the elected members for the aggregation procedure through the selection strategy, and replaces the committee member through the election strategy. Based on the different considerations of model performance and defense, two opposite selection strategies are designed for the sake of both accuracy and robustness. Extensive experiments illustrate that CMFL achieves faster convergence and better accuracy than the typical Federated Learning, in the meanwhile obtaining better robustness than the traditional Byzantine-tolerant algorithms, in the manner of a decentralized approach. In addition, we theoretically analyze and prove the convergence of CMFL under different election and selection strategies, which coincides with the experimental results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2108.00365v2-abstract-full').style.display = 'none'; document.getElementById('2108.00365v2-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 September, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.06039">arXiv:1906.06039</a> <span> [<a href="https://arxiv.org/pdf/1906.06039">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Digital Libraries">cs.DL</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/s11192-019-03311-9">10.1007/s11192-019-03311-9 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Nine Million Book Items and Eleven Million Citations: A Study of Book-Based Scholarly Communication Using OpenCitations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yongjun Zhu</a>, <a href="/search/cs?searchtype=author&query=Yan%2C+E">Erjia Yan</a>, <a href="/search/cs?searchtype=author&query=Peroni%2C+S">Silvio Peroni</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chao Che</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1906.06039v2-abstract-short" style="display: inline;"> Books have been widely used to share information and contribute to human knowledge. However, the quantitative use of books as a method of scholarly communication is relatively unexamined compared to journal articles and conference papers. This study uses the COCI dataset (a comprehensive open citation dataset provided by OpenCitations) to explore books' roles in scholarly communication. The COCI d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.06039v2-abstract-full').style.display = 'inline'; document.getElementById('1906.06039v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.06039v2-abstract-full" style="display: none;"> Books have been widely used to share information and contribute to human knowledge. However, the quantitative use of books as a method of scholarly communication is relatively unexamined compared to journal articles and conference papers. This study uses the COCI dataset (a comprehensive open citation dataset provided by OpenCitations) to explore books' roles in scholarly communication. The COCI data we analyzed includes 445,826,118 citations from 46,534,705 bibliographic entities. By analyzing such a large amount of data, we provide a thorough, multifaceted understanding of books. Among the investigated factors are 1) temporal changes to book citations; 2) book citation distributions; 3) years to citation peak; 4) citation half-life; and 5) characteristics of the most-cited books. Results show that books have received less than 4% of total citations, and have been cited mainly by journal articles. Moreover, 97.96% of books have been cited fewer than ten times. Books take longer than other bibliographic materials to reach peak citation levels, yet are cited for the same duration as journal articles. Most-cited books tend to cover general (yet essential) topics, theories, and technological concepts in mathematics and statistics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.06039v2-abstract-full').style.display = 'none'; document.getElementById('1906.06039v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 December, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1809.10820">arXiv:1809.10820</a> <span> [<a href="https://arxiv.org/pdf/1809.10820">pdf</a>, <a href="https://arxiv.org/format/1809.10820">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"> Inverse Transport Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Che%2C+C">Chengqian Che</a>, <a href="/search/cs?searchtype=author&query=Luan%2C+F">Fujun Luan</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Shuang Zhao</a>, <a href="/search/cs?searchtype=author&query=Bala%2C+K">Kavita Bala</a>, <a href="/search/cs?searchtype=author&query=Gkioulekas%2C+I">Ioannis Gkioulekas</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1809.10820v1-abstract-short" style="display: inline;"> We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination. During training, these networks are evaluated not only in terms of how close they can predict groundtruth parameters, but also in terms of whether the parameters they produce ca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.10820v1-abstract-full').style.display = 'inline'; document.getElementById('1809.10820v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1809.10820v1-abstract-full" style="display: none;"> We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination. During training, these networks are evaluated not only in terms of how close they can predict groundtruth parameters, but also in terms of whether the parameters they produce can be used, together with physically-accurate graphics renderers, to reproduce the input image measurements. To en- able training of inverse transport networks using stochastic gradient descent, we additionally create a general-purpose, physically-accurate differentiable renderer, which can be used to estimate derivatives of images with respect to arbitrary physical scene parameters. Our experiments demonstrate that inverse transport networks can be trained efficiently using differentiable rendering, and that they generalize to scenes with completely unseen geometry and illumination better than networks trained without appearance- matching regularization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.10820v1-abstract-full').style.display = 'none'; document.getElementById('1809.10820v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 September, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2018. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1806.09737">arXiv:1806.09737</a> <span> [<a href="https://arxiv.org/pdf/1806.09737">pdf</a>, <a href="https://arxiv.org/format/1806.09737">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> A Multi-View Ensemble Classification Model for Clinically Actionable Genetic Mutations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+X+S">Xi Sheryl Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+D">Dandi Chen</a>, <a href="/search/cs?searchtype=author&query=Zhu%2C+Y">Yongjun Zhu</a>, <a href="/search/cs?searchtype=author&query=Che%2C+C">Chao Che</a>, <a href="/search/cs?searchtype=author&query=Su%2C+C">Chang Su</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+S">Sendong Zhao</a>, <a href="/search/cs?searchtype=author&query=Min%2C+X">Xu Min</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+F">Fei 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="1806.09737v2-abstract-short" style="display: inline;"> This paper presents details of our winning solutions to the task IV of NIPS 2017 Competition Track entitled Classifying Clinically Actionable Genetic Mutations. The machine learning task aims to classify genetic mutations based on text evidence from clinical literature with promising performance. We develop a novel multi-view machine learning framework with ensemble classification models to solve… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.09737v2-abstract-full').style.display = 'inline'; document.getElementById('1806.09737v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1806.09737v2-abstract-full" style="display: none;"> This paper presents details of our winning solutions to the task IV of NIPS 2017 Competition Track entitled Classifying Clinically Actionable Genetic Mutations. The machine learning task aims to classify genetic mutations based on text evidence from clinical literature with promising performance. We develop a novel multi-view machine learning framework with ensemble classification models to solve the problem. During the Challenge, feature combinations derived from three views including document view, entity text view, and entity name view, which complements each other, are comprehensively explored. As the final solution, we submitted an ensemble of nine basic gradient boosting models which shows the best performance in the evaluation. The approach scores 0.5506 and 0.6694 in terms of logarithmic loss on a fixed split in stage-1 testing phase and 5-fold cross validation respectively, which also makes us ranked as a top-1 team out of more than 1,300 solutions in NIPS 2017 Competition Track IV. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.09737v2-abstract-full').style.display = 'none'; document.getElementById('1806.09737v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 March, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2018. </p> </li> </ol> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository