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 1–17 of 17 results for author: <span class="mathjax">Lei, T</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/eess" aria-role="search"> Searching in archive <strong>eess</strong>. <a href="/search/?searchtype=author&query=Lei%2C+T">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Lei, T"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Lei%2C+T&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Lei, T"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <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/2409.12678">arXiv:2409.12678</a> <span> [<a href="https://arxiv.org/pdf/2409.12678">pdf</a>, <a href="https://arxiv.org/format/2409.12678">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> PMR-Net: Parallel Multi-Resolution Encoder-Decoder Network Framework for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Du%2C+X">Xiaogang Du</a>, <a href="/search/eess?searchtype=author&query=Gu%2C+D">Dongxin Gu</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tao Lei</a>, <a href="/search/eess?searchtype=author&query=Jiao%2C+Y">Yipeng Jiao</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+Y">Yibin Zou</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="2409.12678v1-abstract-short" style="display: inline;"> In recent years, encoder-decoder networks have focused on expanding receptive fields and incorporating multi-scale context to capture global features for objects of varying sizes. However, as networks deepen, they often discard fine spatial details, impairing precise object localization. Additionally, conventional decoders' use of interpolation for upsampling leads to a loss of global context, dim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12678v1-abstract-full').style.display = 'inline'; document.getElementById('2409.12678v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.12678v1-abstract-full" style="display: none;"> In recent years, encoder-decoder networks have focused on expanding receptive fields and incorporating multi-scale context to capture global features for objects of varying sizes. However, as networks deepen, they often discard fine spatial details, impairing precise object localization. Additionally, conventional decoders' use of interpolation for upsampling leads to a loss of global context, diminishing edge segmentation accuracy. To address the above problems, we propose a novel parallel multi-resolution encoder-decoder network, namely PMR-Net for short. First, we design a parallel multi-resolution encoder and a multi-resolution context encoder. The parallel multi-resolution encoder can extract and fuse multi-scale fine-grained local features in parallel for input images with different resolutions. The multi-resolution context encoder fuses the global context semantic features of different receptive fields from different encoder branches to maintain effectively the integrity of global information. Secondly, we design a parallel multi-resolution decoder symmetrical to the structure of parallel multi-resolution encoder. The decoder can continuously supplement the global context features of low-resolution branches to the feature maps of high-resolution branches, and effectively solve the problem of global context feature loss caused by upsampling operation in the decoding process. Extensive experiment results demonstrate that our proposed PMR-Net can achieve more accurate segmentation results than state-of-the-art methods on five public available datasets. Moreover, PMR-Net is also a flexible network framework, which can meet the requirements of different scenarios by adjusting the number of network layers and the number of parallel encoder-decoder branches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12678v1-abstract-full').style.display = 'none'; document.getElementById('2409.12678v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 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/2406.16317">arXiv:2406.16317</a> <span> [<a href="https://arxiv.org/pdf/2406.16317">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="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> SNR-Progressive Model with Harmonic Compensation for Low-SNR Speech Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hou%2C+Z">Zhongshu Hou</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tong Lei</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Q">Qinwen Hu</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+Z">Zhanzhong Cao</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+M">Ming Tang</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jing Lu</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="2406.16317v2-abstract-short" style="display: inline;"> Despite significant progress made in the last decade, deep neural network (DNN) based speech enhancement (SE) still faces the challenge of notable degradation in the quality of recovered speech under low signal-to-noise ratio (SNR) conditions. In this letter, we propose an SNR-progressive speech enhancement model with harmonic compensation for low-SNR SE. Reliable pitch estimation is obtained from… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16317v2-abstract-full').style.display = 'inline'; document.getElementById('2406.16317v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.16317v2-abstract-full" style="display: none;"> Despite significant progress made in the last decade, deep neural network (DNN) based speech enhancement (SE) still faces the challenge of notable degradation in the quality of recovered speech under low signal-to-noise ratio (SNR) conditions. In this letter, we propose an SNR-progressive speech enhancement model with harmonic compensation for low-SNR SE. Reliable pitch estimation is obtained from the intermediate output, which has the benefit of retaining more speech components than the coarse estimate while possessing a significant higher SNR than the input noisy speech. An effective harmonic compensation mechanism is introduced for better harmonic recovery. Extensive ex-periments demonstrate the advantage of our proposed model. A multi-modal speech extraction system based on the proposed backbone model ranks first in the ICASSP 2024 MISP Challenge: https://mispchallenge.github.io/mispchallenge2023/index.html. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16317v2-abstract-full').style.display = 'none'; document.getElementById('2406.16317v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.01060">arXiv:2405.01060</a> <span> [<a href="https://arxiv.org/pdf/2405.01060">pdf</a>, <a href="https://arxiv.org/format/2405.01060">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> A text-based, generative deep learning model for soil reflectance spectrum simulation in the VIS-NIR (400-2499 nm) bands </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tong Lei</a>, <a href="/search/eess?searchtype=author&query=Bailey%2C+B+N">Brian N. Bailey</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="2405.01060v1-abstract-short" style="display: inline;"> Simulating soil reflectance spectra is invaluable for soil-plant radiative modeling and training machine learning models, yet it is difficult as the intricate relationships between soil structure and its constituents. To address this, a fully data-driven soil optics generative model (SOGM) for simulation of soil reflectance spectra based on soil property inputs was developed. The model is trained… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.01060v1-abstract-full').style.display = 'inline'; document.getElementById('2405.01060v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.01060v1-abstract-full" style="display: none;"> Simulating soil reflectance spectra is invaluable for soil-plant radiative modeling and training machine learning models, yet it is difficult as the intricate relationships between soil structure and its constituents. To address this, a fully data-driven soil optics generative model (SOGM) for simulation of soil reflectance spectra based on soil property inputs was developed. The model is trained on an extensive dataset comprising nearly 180,000 soil spectra-property pairs from 17 datasets. It generates soil reflectance spectra from text-based inputs describing soil properties and their values rather than only numerical values and labels in binary vector format. The generative model can simulate output spectra based on an incomplete set of input properties. SOGM is based on the denoising diffusion probabilistic model (DDPM). Two additional sub-models were also built to complement the SOGM: a spectral padding model that can fill in the gaps for spectra shorter than the full visible-near-infrared range (VIS-NIR; 400 to 2499 nm), and a wet soil spectra model that can estimate the effects of water content on soil reflectance spectra given the dry spectrum predicted by the SOGM. The SOGM was up-scaled by coupling with the Helios 3D plant modeling software, which allowed for generation of synthetic aerial images of simulated soil and plant scenes. It can also be easily integrated with soil-plant radiation model used for remote sensin research like PROSAIL. The testing results of the SOGM on new datasets that not included in model training proved that the model can generate reasonable soil reflectance spectra based on available property inputs. The presented models are openly accessible on: https://github.com/GEMINI-Breeding/SOGM_soil_spectra_simulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.01060v1-abstract-full').style.display = 'none'; document.getElementById('2405.01060v1-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 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">The paper has been submitted to Remote sensing of Environment and revised</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.04086">arXiv:2306.04086</a> <span> [<a href="https://arxiv.org/pdf/2306.04086">pdf</a>, <a href="https://arxiv.org/format/2306.04086">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> TEC-Net: Vision Transformer Embrace Convolutional Neural Networks for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+R">Rui Sun</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tao Lei</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Weichuan Zhang</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+Y">Yong Wan</a>, <a href="/search/eess?searchtype=author&query=Xia%2C+Y">Yong Xia</a>, <a href="/search/eess?searchtype=author&query=Nandi%2C+A+K">Asoke K. Nandi</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="2306.04086v3-abstract-short" style="display: inline;"> The hybrid architecture of convolution neural networks (CNN) and Transformer has been the most popular method for medical image segmentation. However, the existing networks based on the hybrid architecture suffer from two problems. First, although the CNN branch can capture image local features by using convolution operation, the vanilla convolution is unable to achieve adaptive extraction of imag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.04086v3-abstract-full').style.display = 'inline'; document.getElementById('2306.04086v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.04086v3-abstract-full" style="display: none;"> The hybrid architecture of convolution neural networks (CNN) and Transformer has been the most popular method for medical image segmentation. However, the existing networks based on the hybrid architecture suffer from two problems. First, although the CNN branch can capture image local features by using convolution operation, the vanilla convolution is unable to achieve adaptive extraction of image features. Second, although the Transformer branch can model the global information of images, the conventional self-attention only focuses on the spatial self-attention of images and ignores the channel and cross-dimensional self-attention leading to low segmentation accuracy for medical images with complex backgrounds. To solve these problems, we propose vision Transformer embrace convolutional neural networks for medical image segmentation (TEC-Net). Our network has two advantages. First, dynamic deformable convolution (DDConv) is designed in the CNN branch, which not only overcomes the difficulty of adaptive feature extraction using fixed-size convolution kernels, but also solves the defect that different inputs share the same convolution kernel parameters, effectively improving the feature expression ability of CNN branch. Second, in the Transformer branch, a (shifted)-window adaptive complementary attention module ((S)W-ACAM) and compact convolutional projection are designed to enable the network to fully learn the cross-dimensional long-range dependency of medical images with few parameters and calculations. Experimental results show that the proposed TEC-Net provides better medical image segmentation results than SOTA methods including CNN and Transformer networks. In addition, our TEC-Net requires fewer parameters and computational costs and does not rely on pre-training. The code is publicly available at https://github.com/SR0920/TEC-Net. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.04086v3-abstract-full').style.display = 'none'; document.getElementById('2306.04086v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">arXiv admin note: substantial text overlap with arXiv:2306.03373</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.03373">arXiv:2306.03373</a> <span> [<a href="https://arxiv.org/pdf/2306.03373">pdf</a>, <a href="https://arxiv.org/format/2306.03373">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div 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/10.24963/ijcai.2023/113">10.24963/ijcai.2023/113 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tao Lei</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+R">Rui Sun</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xuan Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yingbo Wang</a>, <a href="/search/eess?searchtype=author&query=He%2C+X">Xi He</a>, <a href="/search/eess?searchtype=author&query=Nandi%2C+A">Asoke Nandi</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="2306.03373v2-abstract-short" style="display: inline;"> The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features using vanilla convolution, it cannot achieve adaptive feature learning. Second, although a Transformer branch can capture the global features, it ignores the chann… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03373v2-abstract-full').style.display = 'inline'; document.getElementById('2306.03373v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.03373v2-abstract-full" style="display: none;"> The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features using vanilla convolution, it cannot achieve adaptive feature learning. Second, although a Transformer branch can capture the global features, it ignores the channel and cross-dimensional self-attention, resulting in a low segmentation accuracy on complex-content images. To address these challenges, we propose a novel hybrid architecture of convolutional neural networks hand in hand with vision Transformers (CiT-Net) for medical image segmentation. Our network has two advantages. First, we design a dynamic deformable convolution and apply it to the CNNs branch, which overcomes the weak feature extraction ability due to fixed-size convolution kernels and the stiff design of sharing kernel parameters among different inputs. Second, we design a shifted-window adaptive complementary attention module and a compact convolutional projection. We apply them to the Transformer branch to learn the cross-dimensional long-term dependency for medical images. Experimental results show that our CiT-Net provides better medical image segmentation results than popular SOTA methods. Besides, our CiT-Net requires lower parameters and less computational costs and does not rely on pre-training. The code is publicly available at https://github.com/SR0920/CiT-Net. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03373v2-abstract-full').style.display = 'none'; document.getElementById('2306.03373v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 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">9 pages, 3 figures, 3 tables</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> The 32nd International Joint Conference on Artificial Intelligence, IJCAI2023, MACAO </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.00812">arXiv:2306.00812</a> <span> [<a href="https://arxiv.org/pdf/2306.00812">pdf</a>, <a href="https://arxiv.org/format/2306.00812">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Le%2C+X">Xiaohuai Le</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tong Lei</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+L">Li Chen</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Y">Yiqing Guo</a>, <a href="/search/eess?searchtype=author&query=He%2C+C">Chao He</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+C">Cheng Chen</a>, <a href="/search/eess?searchtype=author&query=Xia%2C+X">Xianjun Xia</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+H">Hua Gao</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+Y">Yijian Xiao</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+P">Piao Ding</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenyi Song</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jing Lu</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="2306.00812v1-abstract-short" style="display: inline;"> With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. The signal processing-based comb filters used in RNNoise and PercepNet have limited performance and may cause speech quality degradation due to inaccura… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00812v1-abstract-full').style.display = 'inline'; document.getElementById('2306.00812v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.00812v1-abstract-full" style="display: none;"> With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. The signal processing-based comb filters used in RNNoise and PercepNet have limited performance and may cause speech quality degradation due to inaccurate fundamental frequency estimation. To tackle this problem, we propose a learnable comb filter to enhance harmonics. Based on the sub-band model, we design a DNN-based fundamental frequency estimator to estimate the discrete fundamental frequencies and a comb filter for harmonic enhancement, which are trained via an end-to-end pattern. The experiments show the advantages of our proposed method over PecepNet and DeepFilterNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00812v1-abstract-full').style.display = 'none'; document.getElementById('2306.00812v1-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 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">accepted by Interspeech 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/2207.11108">arXiv:2207.11108</a> <span> [<a href="https://arxiv.org/pdf/2207.11108">pdf</a>, <a href="https://arxiv.org/format/2207.11108">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> <div 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.2022.3190738">10.1109/TASLP.2022.3190738 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Inference skipping for more efficient real-time speech enhancement with parallel RNNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Le%2C+X">Xiaohuai Le</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tong Lei</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+K">Kai Chen</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jing Lu</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="2207.11108v1-abstract-short" style="display: inline;"> Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational cost. Typical compression methods such as pruning and quantization do not make good use of the data characteristics. In this paper, we introduce the Skip-RNN str… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.11108v1-abstract-full').style.display = 'inline'; document.getElementById('2207.11108v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.11108v1-abstract-full" style="display: none;"> Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational cost. Typical compression methods such as pruning and quantization do not make good use of the data characteristics. In this paper, we introduce the Skip-RNN strategy into speech enhancement models with parallel RNNs. The states of the RNNs update intermittently without interrupting the update of the output mask, which leads to significant reduction of computational load without evident audio artifacts. To better leverage the difference between the voice and the noise, we further regularize the skipping strategy with voice activity detection (VAD) guidance, saving more computational load. Experiments on a high-performance speech enhancement model, dual-path convolutional recurrent network (DPCRN), show the superiority of our strategy over strategies like network pruning or directly training a smaller model. We also validate the generalization of the proposed strategy on two other competitive speech enhancement models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.11108v1-abstract-full').style.display = 'none'; document.getElementById('2207.11108v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 8 figures, accepted by IEEE/ACM TASLP</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2110.05571">arXiv:2110.05571</a> <span> [<a href="https://arxiv.org/pdf/2110.05571">pdf</a>, <a href="https://arxiv.org/format/2110.05571">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Pan%2C+J">Jing Pan</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tao Lei</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+K">Kwangyoun Kim</a>, <a href="/search/eess?searchtype=author&query=Han%2C+K">Kyu Han</a>, <a href="/search/eess?searchtype=author&query=Watanabe%2C+S">Shinji Watanabe</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="2110.05571v1-abstract-short" style="display: inline;"> The Transformer architecture has been well adopted as a dominant architecture in most sequence transduction tasks including automatic speech recognition (ASR), since its attention mechanism excels in capturing long-range dependencies. While models built solely upon attention can be better parallelized than regular RNN, a novel network architecture, SRU++, was recently proposed. By combining the fa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.05571v1-abstract-full').style.display = 'inline'; document.getElementById('2110.05571v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2110.05571v1-abstract-full" style="display: none;"> The Transformer architecture has been well adopted as a dominant architecture in most sequence transduction tasks including automatic speech recognition (ASR), since its attention mechanism excels in capturing long-range dependencies. While models built solely upon attention can be better parallelized than regular RNN, a novel network architecture, SRU++, was recently proposed. By combining the fast recurrence and attention mechanism, SRU++ exhibits strong capability in sequence modeling and achieves near-state-of-the-art results in various language modeling and machine translation tasks with improved compute efficiency. In this work, we present the advantages of applying SRU++ in ASR tasks by comparing with Conformer across multiple ASR benchmarks and study how the benefits can be generalized to long-form speech inputs. On the popular LibriSpeech benchmark, our SRU++ model achieves 2.0% / 4.7% WER on test-clean / test-other, showing competitive performances compared with the state-of-the-art Conformer encoder under the same set-up. Specifically, SRU++ can surpass Conformer on long-form speech input with a large margin, based on our analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2110.05571v1-abstract-full').style.display = 'none'; document.getElementById('2110.05571v1-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, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2009.13120">arXiv:2009.13120</a> <span> [<a href="https://arxiv.org/pdf/2009.13120">pdf</a>, <a href="https://arxiv.org/format/2009.13120">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div 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/10.1049/ipr2.12419">10.1049/ipr2.12419 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Medical Image Segmentation Using Deep Learning: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+R">Risheng Wang</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tao Lei</a>, <a href="/search/eess?searchtype=author&query=Cui%2C+R">Ruixia Cui</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+B">Bingtao Zhang</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+H">Hongying Meng</a>, <a href="/search/eess?searchtype=author&query=Nandi%2C+A+K">Asoke K. Nandi</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="2009.13120v3-abstract-short" style="display: inline;"> Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field. In this paper, we present a comprehensive thematic survey on medical image segmentation using deep learning techniques. This paper makes two original contributions. Firstly, compared to traditional surveys that directly divide litera… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.13120v3-abstract-full').style.display = 'inline'; document.getElementById('2009.13120v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2009.13120v3-abstract-full" style="display: none;"> Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field. In this paper, we present a comprehensive thematic survey on medical image segmentation using deep learning techniques. This paper makes two original contributions. Firstly, compared to traditional surveys that directly divide literatures of deep learning on medical image segmentation into many groups and introduce literatures in detail for each group, we classify currently popular literatures according to a multi-level structure from coarse to fine. Secondly, this paper focuses on supervised and weakly supervised learning approaches, without including unsupervised approaches since they have been introduced in many old surveys and they are not popular currently. For supervised learning approaches, we analyze literatures in three aspects: the selection of backbone networks, the design of network blocks, and the improvement of loss functions. For weakly supervised learning approaches, we investigate literature according to data augmentation, transfer learning, and interactive segmentation, separately. Compared to existing surveys, this survey classifies the literatures very differently from before and is more convenient for readers to understand the relevant rationale and will guide them to think of appropriate improvements in medical image segmentation based on deep learning approaches. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2009.13120v3-abstract-full').style.display = 'none'; document.getElementById('2009.13120v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2005.10469">arXiv:2005.10469</a> <span> [<a href="https://arxiv.org/pdf/2005.10469">pdf</a>, <a href="https://arxiv.org/format/2005.10469">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Pan%2C+J">Jing Pan</a>, <a href="/search/eess?searchtype=author&query=Shapiro%2C+J">Joshua Shapiro</a>, <a href="/search/eess?searchtype=author&query=Wohlwend%2C+J">Jeremy Wohlwend</a>, <a href="/search/eess?searchtype=author&query=Han%2C+K+J">Kyu J. Han</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tao Lei</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+T">Tao 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="2005.10469v1-abstract-short" style="display: inline;"> In this paper we present state-of-the-art (SOTA) performance on the LibriSpeech corpus with two novel neural network architectures, a multistream CNN for acoustic modeling and a self-attentive simple recurrent unit (SRU) for language modeling. In the hybrid ASR framework, the multistream CNN acoustic model processes an input of speech frames in multiple parallel pipelines where each stream has a u… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.10469v1-abstract-full').style.display = 'inline'; document.getElementById('2005.10469v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2005.10469v1-abstract-full" style="display: none;"> In this paper we present state-of-the-art (SOTA) performance on the LibriSpeech corpus with two novel neural network architectures, a multistream CNN for acoustic modeling and a self-attentive simple recurrent unit (SRU) for language modeling. In the hybrid ASR framework, the multistream CNN acoustic model processes an input of speech frames in multiple parallel pipelines where each stream has a unique dilation rate for diversity. Trained with the SpecAugment data augmentation method, it achieves relative word error rate (WER) improvements of 4% on test-clean and 14% on test-other. We further improve the performance via N-best rescoring using a 24-layer self-attentive SRU language model, achieving WERs of 1.75% on test-clean and 4.46% on test-other. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2005.10469v1-abstract-full').style.display = 'none'; document.getElementById('2005.10469v1-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 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to Interspeech 2020</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.05033">arXiv:1911.05033</a> <span> [<a href="https://arxiv.org/pdf/1911.05033">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1364/OE.383240">10.1364/OE.383240 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Visual cryptography in single-pixel imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jiao%2C+S">Shuming Jiao</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+J">Jun Feng</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yang Gao</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Ting Lei</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+X">Xiaocong Yuan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1911.05033v1-abstract-short" style="display: inline;"> Two novel visual cryptography (VC) schemes are proposed by combining VC with single-pixel imaging (SPI) for the first time. It is pointed out that the overlapping of visual key images in VC is similar to the superposition of pixel intensities by a single-pixel detector in SPI. In the first scheme, QR-code VC is designed by using opaque sheets instead of transparent sheets. The secret image can be… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.05033v1-abstract-full').style.display = 'inline'; document.getElementById('1911.05033v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.05033v1-abstract-full" style="display: none;"> Two novel visual cryptography (VC) schemes are proposed by combining VC with single-pixel imaging (SPI) for the first time. It is pointed out that the overlapping of visual key images in VC is similar to the superposition of pixel intensities by a single-pixel detector in SPI. In the first scheme, QR-code VC is designed by using opaque sheets instead of transparent sheets. The secret image can be recovered when identical illumination patterns are projected onto multiple visual key images and a single detector is used to record the total light intensities. In the second scheme, the secret image is shared by multiple illumination pattern sequences and it can be recovered when the visual key patterns are projected onto identical items. The application of VC can be extended to more diversified scenarios by our proposed schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.05033v1-abstract-full').style.display = 'none'; document.getElementById('1911.05033v1-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 November, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1911.00353">arXiv:1911.00353</a> <span> [<a href="https://arxiv.org/pdf/1911.00353">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 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/10.1364/OE.382319">10.1364/OE.382319 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Does deep learning always outperform simple linear regression in optical imaging? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jiao%2C+S">Shuming Jiao</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yang Gao</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+J">Jun Feng</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Ting Lei</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+X">Xiaocong Yuan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1911.00353v2-abstract-short" style="display: inline;"> Deep learning has been extensively applied in many optical imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in optical imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box optical imaging problems in som… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.00353v2-abstract-full').style.display = 'inline'; document.getElementById('1911.00353v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1911.00353v2-abstract-full" style="display: none;"> Deep learning has been extensively applied in many optical imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in optical imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box optical imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1911.00353v2-abstract-full').style.display = 'none'; document.getElementById('1911.00353v2-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 January, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 October, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1910.11222">arXiv:1910.11222</a> <span> [<a href="https://arxiv.org/pdf/1910.11222">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"> Data hiding in complex-amplitude modulation using a digital micromirror device </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jiao%2C+S">Shuming Jiao</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+D">Dongfang Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+C">Chonglei Zhang</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yang Gao</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Ting Lei</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+X">Xiaocong Yuan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1910.11222v1-abstract-short" style="display: inline;"> A digital micromirror device (DMD) is an amplitude-type spatial light modulator. However, a complex-amplitude light modulation with a DMD can be achieved using the superpixel scheme. In the superpixel scheme, we notice that multiple different DMD local block patterns may correspond to the same complex superpixel value. Based on this inherent encoding redundancy, a large amount of external data can… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.11222v1-abstract-full').style.display = 'inline'; document.getElementById('1910.11222v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1910.11222v1-abstract-full" style="display: none;"> A digital micromirror device (DMD) is an amplitude-type spatial light modulator. However, a complex-amplitude light modulation with a DMD can be achieved using the superpixel scheme. In the superpixel scheme, we notice that multiple different DMD local block patterns may correspond to the same complex superpixel value. Based on this inherent encoding redundancy, a large amount of external data can be embedded into the DMD pattern without extra cost. Meanwhile, the original complex light field information carried by the DMD pattern is fully preserved. This proposed scheme is favorable for applications such as secure information transmission and copyright protection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1910.11222v1-abstract-full').style.display = 'none'; document.getElementById('1910.11222v1-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1906.08411">arXiv:1906.08411</a> <span> [<a href="https://arxiv.org/pdf/1906.08411">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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 novel linear battery energy storage system (BESS) life loss calculation model for BESS-integrated wind farm in scheduled power tracking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gui%2C+Q">Qiang Gui</a>, <a href="/search/eess?searchtype=author&query=Su%2C+H">Hao Su</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+D">Donghan Feng</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+Y">Yun Zhou</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+R">Ran Xu</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Ting Lei</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="1906.08411v2-abstract-short" style="display: inline;"> Recently, rapid development of battery technology makes it feasible to integrate renewable generations with battery energy storage system (BESS). The consideration of BESS life loss for different BESS application scenarios is economic imperative. In this paper, a novel linear BESS life loss calculation model for BESS-integrated wind farm in scheduled power tracking is proposed. Firstly, based on t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.08411v2-abstract-full').style.display = 'inline'; document.getElementById('1906.08411v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1906.08411v2-abstract-full" style="display: none;"> Recently, rapid development of battery technology makes it feasible to integrate renewable generations with battery energy storage system (BESS). The consideration of BESS life loss for different BESS application scenarios is economic imperative. In this paper, a novel linear BESS life loss calculation model for BESS-integrated wind farm in scheduled power tracking is proposed. Firstly, based on the life cycle times-depth of discharge (DOD) relation-curve, the BESS life loss coefficient for unit throughput energy with different state of charge (SOC) can be determined from the life cycle times-DOD relation-curve fitting function directly. Secondly, as unidirectional variation of SOC in a single time step, the BESS life loss can be calculated through integration of the life loss coefficient-SOC relation function. A linear BESS life loss calculation model is established through self-optimal piecewise linearization of the primitive function of the life loss coefficient-SOC relation function. Thirdly, the proposed life loss calculation model is incorporated in the BESS-integrated wind farm scheduled power tracking optimization. Case studies demonstrate that with the proposed method, the BESS life loss item can be incorporated in the optimization model effectively, and the scheduled power tracking cost of the BESS-integrated wind farm can be determined and optimized more comprehensively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1906.08411v2-abstract-full').style.display = 'none'; document.getElementById('1906.08411v2-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, 2019; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2019. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This article has been accepted in the 2019 International Conference on Renewable Power Generation (RPG 2019), Shanghai, China, October 24-25, 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1905.13594">arXiv:1905.13594</a> <span> [<a href="https://arxiv.org/pdf/1905.13594">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="Cryptography and Security">cs.CR</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"> Known-plaintext attack and ciphertext-only attack for encrypted single-pixel imaging </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jiao%2C+S">Shuming Jiao</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yang Gao</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Ting Lei</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+Z">Zhenwei Xie</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+X">Xiaocong Yuan</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="1905.13594v1-abstract-short" style="display: inline;"> In many previous works, a single-pixel imaging (SPI) system is constructed as an optical image encryption system. Unauthorized users are not able to reconstruct the plaintext image from the ciphertext intensity sequence without knowing the illumination pattern key. However, little cryptanalysis about encrypted SPI has been investigated in the past. In this work, we propose a known-plaintext attack… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.13594v1-abstract-full').style.display = 'inline'; document.getElementById('1905.13594v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1905.13594v1-abstract-full" style="display: none;"> In many previous works, a single-pixel imaging (SPI) system is constructed as an optical image encryption system. Unauthorized users are not able to reconstruct the plaintext image from the ciphertext intensity sequence without knowing the illumination pattern key. However, little cryptanalysis about encrypted SPI has been investigated in the past. In this work, we propose a known-plaintext attack scheme and a ciphertext-only attack scheme to an encrypted SPI system for the first time. The known-plaintext attack is implemented by interchanging the roles of illumination patterns and object images in the SPI model. The ciphertext-only attack is implemented based on the statistical features of single-pixel intensity values. The two schemes can crack encrypted SPI systems and successfully recover the key containing correct illumination patterns. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1905.13594v1-abstract-full').style.display = 'none'; document.getElementById('1905.13594v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 May, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1902.07985">arXiv:1902.07985</a> <span> [<a href="https://arxiv.org/pdf/1902.07985">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 class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.optcom.2020.125476">10.1016/j.optcom.2020.125476 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Multiple-image encryption and hiding with an optical diffractive neural network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yang Gao</a>, <a href="/search/eess?searchtype=author&query=Jiao%2C+S">Shuming Jiao</a>, <a href="/search/eess?searchtype=author&query=Fang%2C+J">Juncheng Fang</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Ting Lei</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+Z">Zhenwei Xie</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+X">Xiaocong Yuan</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="1902.07985v2-abstract-short" style="display: inline;"> A cascaded phase-only mask architecture (or an optical diffractive neural network) can be employed for different optical information processing tasks such as pattern recognition, orbital angular momentum (OAM) mode conversion, image salience detection and image encryption. However, for optical encryption and watermarking applications, such a system usually cannot process multiple pairs of input im… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.07985v2-abstract-full').style.display = 'inline'; document.getElementById('1902.07985v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1902.07985v2-abstract-full" style="display: none;"> A cascaded phase-only mask architecture (or an optical diffractive neural network) can be employed for different optical information processing tasks such as pattern recognition, orbital angular momentum (OAM) mode conversion, image salience detection and image encryption. However, for optical encryption and watermarking applications, such a system usually cannot process multiple pairs of input images and output images simultaneously. In our proposed scheme, multiple input images can be simultaneously fed to an optical diffractive neural network (DNN) system and each corresponding output image will be displayed in a non-overlap sub-region in the output imaging plane. Each input image undergoes a different optical transform in an independent channel within the same system. The multiple cascaded phase masks in the system can be effectively optimized by a wavefront matching algorithm. Similar to recent optical pattern recognition and mode conversion works, the orthogonality property is employed to design a multiplexed DNN. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1902.07985v2-abstract-full').style.display = 'none'; document.getElementById('1902.07985v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 February, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 February, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1806.01340">arXiv:1806.01340</a> <span> [<a href="https://arxiv.org/pdf/1806.01340">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"> Design of optimal illumination patterns in single-pixel imaging using image dictionaries </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Feng%2C+J">Jun Feng</a>, <a href="/search/eess?searchtype=author&query=Jiao%2C+S">Shuming Jiao</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+Y">Yang Gao</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Ting Lei</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+X">Xiaocong Yuan</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="1806.01340v2-abstract-short" style="display: inline;"> Single-pixel imaging (SPI) has a major drawback that many sequential illuminations are required for capturing one single image with long acquisition time. Basis illumination patterns such as Fourier patterns and Hadamard patterns can achieve much better imaging efficiency than random patterns. But the performance is still sub-optimal since the basis patterns are fixed and non-adaptive for varying… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.01340v2-abstract-full').style.display = 'inline'; document.getElementById('1806.01340v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1806.01340v2-abstract-full" style="display: none;"> Single-pixel imaging (SPI) has a major drawback that many sequential illuminations are required for capturing one single image with long acquisition time. Basis illumination patterns such as Fourier patterns and Hadamard patterns can achieve much better imaging efficiency than random patterns. But the performance is still sub-optimal since the basis patterns are fixed and non-adaptive for varying object images. This Letter proposes a novel scheme for designing and optimizing the illumination patterns adaptively from an image dictionary by extracting the common image features using principal component analysis (PCA). Simulation and experimental results reveal that our proposed scheme outperforms conventional Fourier SPI in terms of imaging efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1806.01340v2-abstract-full').style.display = 'none'; document.getElementById('1806.01340v2-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 January, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 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