index.html 44 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948
  1. <!doctype html>
  2. <html>
  3. <head>
  4. <meta charset="utf-8">
  5. <meta http-equiv="X-UA-Compatible" content="chrome=1">
  6. <title>Awesome-deep-vision by kjw0612</title>
  7. <link rel="stylesheet" href="stylesheets/styles.css">
  8. <link rel="stylesheet" href="stylesheets/github-dark.css">
  9. <script src="javascripts/scale.fix.js"></script>
  10. <meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=no">
  11. <!--[if lt IE 9]>
  12. <script src="//html5shiv.googlecode.com/svn/trunk/html5.js"></script>
  13. <![endif]-->
  14. </head>
  15. <body>
  16. <div class="wrapper">
  17. <header>
  18. <h1>Awesome-deep-vision</h1>
  19. <p>A curated list of deep learning resources for computer vision </p>
  20. <p class="view"><a href="https://github.com/kjw0612/awesome-deep-vision">View the Project on GitHub <small>kjw0612/awesome-deep-vision</small></a></p>
  21. <ul>
  22. <li><a href="https://github.com/kjw0612/awesome-deep-vision/zipball/master">Download <strong>ZIP File</strong></a></li>
  23. <li><a href="https://github.com/kjw0612/awesome-deep-vision/tarball/master">Download <strong>TAR Ball</strong></a></li>
  24. <li><a href="https://github.com/kjw0612/awesome-deep-vision">View On <strong>GitHub</strong></a></li>
  25. </ul>
  26. </header>
  27. <section>
  28. <h1>
  29. <a id="awesome-deep-vision-" class="anchor" href="#awesome-deep-vision-" aria-hidden="true"><span class="octicon octicon-link"></span></a>Awesome Deep Vision <a href="https://github.com/sindresorhus/awesome"><img src="https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg" alt="Awesome"></a>
  30. </h1>
  31. <p>A curated list of deep learning resources for computer vision, inspired by <a href="https://github.com/ziadoz/awesome-php">awesome-php</a> and <a href="https://github.com/jbhuang0604/awesome-computer-vision">awesome-computer-vision</a>.</p>
  32. <p>Maintainers - <a href="http://github.com/kjw0612">Jiwon Kim</a>, <a href="https://github.com/hmyeong">Heesoo Myeong</a>, <a href="http://github.com/myungsub">Myungsub Choi</a>, <a href="http://github.com/deruci">Jung Kwon Lee</a></p>
  33. <p>We are looking for a maintainer! Let me know (<a href="mailto:jiwon@alum.mit.edu">jiwon@alum.mit.edu</a>) if interested.</p>
  34. <h2>
  35. <a id="contributing" class="anchor" href="#contributing" aria-hidden="true"><span class="octicon octicon-link"></span></a>Contributing</h2>
  36. <p>Please feel free to <a href="https://github.com/kjw0612/awesome-deep-vision/pulls">pull requests</a> to add papers.</p>
  37. <p><a href="https://gitter.im/kjw0612/awesome-deep-vision?utm_source=badge&amp;utm_medium=badge&amp;utm_campaign=pr-badge&amp;utm_content=badge"><img src="https://badges.gitter.im/Join%20Chat.svg" alt="Join the chat at https://gitter.im/kjw0612/awesome-deep-vision"></a></p>
  38. <h2>
  39. <a id="sharing" class="anchor" href="#sharing" aria-hidden="true"><span class="octicon octicon-link"></span></a>Sharing</h2>
  40. <ul>
  41. <li><a href="http://twitter.com/home?status=http://jiwonkim.org/awesome-deep-vision%0ADeep%20Learning%20Resources%20for%20Computer%20Vision">Share on Twitter</a></li>
  42. <li><a href="http://www.facebook.com/sharer/sharer.php?u=https://jiwonkim.org/awesome-deep-vision">Share on Facebook</a></li>
  43. <li><a href="http://plus.google.com/share?url=https://jiwonkim.org/awesome-deep-vision">Share on Google Plus</a></li>
  44. <li><a href="http://www.linkedin.com/shareArticle?mini=true&amp;url=https://jiwonkim.org/awesome-deep-vision&amp;title=Awesome%20Deep%20Vision&amp;summary=&amp;source=">Share on LinkedIn</a></li>
  45. </ul>
  46. <h2>
  47. <a id="table-of-contents" class="anchor" href="#table-of-contents" aria-hidden="true"><span class="octicon octicon-link"></span></a>Table of Contents</h2>
  48. <ul>
  49. <li>
  50. <a href="#papers">Papers</a>
  51. <ul>
  52. <li><a href="#imagenet-classification">ImageNet Classification</a></li>
  53. <li><a href="#object-detection">Object Detection</a></li>
  54. <li><a href="#object-tracking">Object Tracking</a></li>
  55. <li>
  56. <a href="#low-level-vision">Low-Level Vision</a>
  57. <ul>
  58. <li><a href="#super-resolution">Super-Resolution</a></li>
  59. <li><a href="#other-applications">Other Applications</a></li>
  60. </ul>
  61. </li>
  62. <li><a href="#edge-detection">Edge Detection</a></li>
  63. <li><a href="#semantic-segmentation">Semantic Segmentation</a></li>
  64. <li><a href="#visual-attention-and-saliency">Visual Attention and Saliency</a></li>
  65. <li><a href="#object-recognition">Object Recognition</a></li>
  66. <li><a href="#understanding-cnn">Understanding CNN</a></li>
  67. <li>
  68. <a href="#image-and-language">Image and Language</a>
  69. <ul>
  70. <li><a href="#image-captioning">Image Captioning</a></li>
  71. <li><a href="#video-captioning">Video Captioning</a></li>
  72. <li><a href="#question-answering">Question Answering</a></li>
  73. </ul>
  74. </li>
  75. <li><a href="#other-topics">Other Topics</a></li>
  76. </ul>
  77. </li>
  78. <li><a href="#courses">Courses</a></li>
  79. <li><a href="#books">Books</a></li>
  80. <li><a href="#videos">Videos</a></li>
  81. <li>
  82. <a href="#software">Software</a>
  83. <ul>
  84. <li><a href="#framework">Framework</a></li>
  85. <li><a href="#applications">Applications</a></li>
  86. </ul>
  87. </li>
  88. <li><a href="#tutorials">Tutorials</a></li>
  89. <li><a href="#blogs">Blogs</a></li>
  90. </ul>
  91. <h2>
  92. <a id="papers" class="anchor" href="#papers" aria-hidden="true"><span class="octicon octicon-link"></span></a>Papers</h2>
  93. <h3>
  94. <a id="imagenet-classification" class="anchor" href="#imagenet-classification" aria-hidden="true"><span class="octicon octicon-link"></span></a>ImageNet Classification</h3>
  95. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8451949/327b9566-2022-11e5-8b34-53b4a64c13ad.PNG" alt="classification">
  96. (from Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, NIPS, 2012.)</p>
  97. <ul>
  98. <li>Microsoft (PReLu/Weight Initialization) <a href="http://arxiv.org/pdf/1502.01852">[Paper]</a>
  99. <ul>
  100. <li>Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, arXiv:1502.01852.</li>
  101. </ul>
  102. </li>
  103. <li>Batch Normalization <a href="http://arxiv.org/pdf/1502.03167">[Paper]</a>
  104. <ul>
  105. <li>Sergey Ioffe, Christian Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, arXiv:1502.03167.</li>
  106. </ul>
  107. </li>
  108. <li>GoogLeNet <a href="http://arxiv.org/pdf/1409.4842">[Paper]</a>
  109. <ul>
  110. <li>Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, CVPR, 2015.</li>
  111. </ul>
  112. </li>
  113. <li>VGG-Net <a href="http://www.robots.ox.ac.uk/%7Evgg/research/very_deep/">[Web]</a> <a href="http://arxiv.org/pdf/1409.1556">[Paper]</a>
  114. <ul>
  115. <li>Karen Simonyan and Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Visual Recognition, ICLR, 2015.</li>
  116. </ul>
  117. </li>
  118. <li>AlexNet <a href="http://books.nips.cc/papers/files/nips25/NIPS2012_0534.pdf">[Paper]</a>
  119. <ul>
  120. <li>Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, NIPS, 2012.</li>
  121. </ul>
  122. </li>
  123. </ul>
  124. <h3>
  125. <a id="object-detection" class="anchor" href="#object-detection" aria-hidden="true"><span class="octicon octicon-link"></span></a>Object Detection</h3>
  126. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8452063/f76ba500-2022-11e5-8db1-2cd5d490e3b3.PNG" alt="object_detection">
  127. (from Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, arXiv:1506.01497.)</p>
  128. <ul>
  129. <li>OverFeat, NYU <a href="http://arxiv.org/pdf/1312.6229.pdf">[Paper]</a>
  130. <ul>
  131. <li>OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, ICLR, 2014.</li>
  132. </ul>
  133. </li>
  134. <li>R-CNN, UC Berkeley <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Girshick_Rich_Feature_Hierarchies_2014_CVPR_paper.pdf">[Paper-CVPR14]</a> <a href="http://arxiv.org/pdf/1311.2524">[Paper-arXiv14]</a>
  135. <ul>
  136. <li>Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR, 2014.</li>
  137. </ul>
  138. </li>
  139. <li>SPP, Microsoft Research <a href="http://arxiv.org/pdf/1406.4729">[Paper]</a>
  140. <ul>
  141. <li>Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, ECCV, 2014.</li>
  142. </ul>
  143. </li>
  144. <li>Fast R-CNN, Microsoft Research <a href="http://arxiv.org/pdf/1504.08083">[Paper]</a>
  145. <ul>
  146. <li>Ross Girshick, Fast R-CNN, arXiv:1504.08083.</li>
  147. </ul>
  148. </li>
  149. <li>Faster R-CNN, Microsoft Research <a href="http://arxiv.org/pdf/1506.01497">[Paper]</a>
  150. <ul>
  151. <li>Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, arXiv:1506.01497.</li>
  152. </ul>
  153. </li>
  154. <li>R-CNN minus R, Oxford <a href="http://arxiv.org/pdf/1506.06981">[Paper]</a>
  155. <ul>
  156. <li>Karel Lenc, Andrea Vedaldi, R-CNN minus R, arXiv:1506.06981.</li>
  157. </ul>
  158. </li>
  159. <li>End-to-end people detection in crowded scenes <a href="http://arxiv.org/abs/1506.04878">[Paper]</a>
  160. <ul>
  161. <li>Russell Stewart, Mykhaylo Andriluka, End-to-end people detection in crowded scenes, arXiv:1506.04878.</li>
  162. </ul>
  163. </li>
  164. </ul>
  165. <h3>
  166. <a id="object-tracking" class="anchor" href="#object-tracking" aria-hidden="true"><span class="octicon octicon-link"></span></a>Object Tracking</h3>
  167. <ul>
  168. <li>Seunghoon Hong, Tackgeun You, Suha Kwak, Bohyung Han, Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network, arXiv:1502.06796. <a href="http://arxiv.org/pdf/1502.06796">[Paper]</a>
  169. </li>
  170. <li>Hanxi Li, Yi Li and Fatih Porikli, DeepTrack: Learning Discriminative Feature Representations by Convolutional Neural Networks for Visual Tracking, BMVC, 2014. <a href="http://www.bmva.org/bmvc/2014/files/paper028.pdf">[Paper]</a>
  171. </li>
  172. <li>N Wang, DY Yeung, Learning a Deep Compact Image Representation for Visual Tracking, NIPS, 2013. <a href="http://winsty.net/papers/dlt.pdf">[Paper]</a>
  173. </li>
  174. <li>Chao Ma, Jia-Bin Huang, Xiaokang Yang and Ming-Hsuan Yang, "Hierarchical Convolutional Features for Visual Tracking", ICCV 2015 <a href="https://github.com/jbhuang0604/CF2">[GitHub]</a>
  175. </li>
  176. </ul>
  177. <h3>
  178. <a id="low-level-vision" class="anchor" href="#low-level-vision" aria-hidden="true"><span class="octicon octicon-link"></span></a>Low-Level Vision</h3>
  179. <h4>
  180. <a id="super-resolution" class="anchor" href="#super-resolution" aria-hidden="true"><span class="octicon octicon-link"></span></a>Super-Resolution</h4>
  181. <ul>
  182. <li>Super-Resolution (SRCNN) <a href="http://mmlab.ie.cuhk.edu.hk/projects/SRCNN.html">[Web]</a> <a href="http://personal.ie.cuhk.edu.hk/%7Eccloy/files/eccv_2014_deepresolution.pdf">[Paper-ECCV14]</a> <a href="http://arxiv.org/pdf/1501.00092.pdf">[Paper-arXiv15]</a>
  183. <ul>
  184. <li>Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, Learning a Deep Convolutional Network for Image Super-Resolution, ECCV, 2014.</li>
  185. <li>Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, Image Super-Resolution Using Deep Convolutional Networks, arXiv:1501.00092.</li>
  186. </ul>
  187. </li>
  188. <li>Very Deep Super-Resolution
  189. <ul>
  190. <li>Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee, Accurate Image Super-Resolution Using Very Deep Convolutional Networks, arXiv:1511.04587, 2015. <a href="http://arxiv.org/abs/1511.04587">[Paper]</a>
  191. </li>
  192. </ul>
  193. </li>
  194. <li>Deeply-Recursive Convolutional Network
  195. <ul>
  196. <li>Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee, Deeply-Recursive Convolutional Network for Image Super-Resolution, arXiv:1511.04491, 2015. <a href="http://arxiv.org/abs/1511.04491">[Paper]</a>
  197. </li>
  198. </ul>
  199. </li>
  200. <li>Others
  201. <ul>
  202. <li>Osendorfer, Christian, Hubert Soyer, and Patrick van der Smagt, Image Super-Resolution with Fast Approximate Convolutional Sparse Coding, ICONIP, 2014. <a href="http://www.brml.org/uploads/tx_sibibtex/281.pdf">[Paper ICONIP-2014]</a>
  203. </li>
  204. </ul>
  205. </li>
  206. </ul>
  207. <h4>
  208. <a id="other-applications" class="anchor" href="#other-applications" aria-hidden="true"><span class="octicon octicon-link"></span></a>Other Applications</h4>
  209. <ul>
  210. <li>Optical Flow (FlowNet) <a href="http://arxiv.org/pdf/1504.06852">[Paper]</a>
  211. <ul>
  212. <li>Philipp Fischer, Alexey Dosovitskiy, Eddy Ilg, Philip Häusser, Caner Hazırbaş, Vladimir Golkov, Patrick van der Smagt, Daniel Cremers, Thomas Brox, FlowNet: Learning Optical Flow with Convolutional Networks, arXiv:1504.06852.</li>
  213. </ul>
  214. </li>
  215. <li>Compression Artifacts Reduction <a href="http://arxiv.org/pdf/1504.06993">[Paper-arXiv15]</a>
  216. <ul>
  217. <li>Chao Dong, Yubin Deng, Chen Change Loy, Xiaoou Tang, Compression Artifacts Reduction by a Deep Convolutional Network, arXiv:1504.06993.</li>
  218. </ul>
  219. </li>
  220. <li>Blur Removal
  221. <ul>
  222. <li>Christian J. Schuler, Michael Hirsch, Stefan Harmeling, Bernhard Schölkopf, Learning to Deblur, arXiv:1406.7444 <a href="http://arxiv.org/pdf/1406.7444.pdf">[Paper]</a>
  223. </li>
  224. <li>Jian Sun, Wenfei Cao, Zongben Xu, Jean Ponce, Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal, CVPR, 2015 <a href="http://arxiv.org/pdf/1503.00593">[Paper]</a>
  225. </li>
  226. </ul>
  227. </li>
  228. <li>Image Deconvolution <a href="http://lxu.me/projects/dcnn/">[Web]</a> <a href="http://lxu.me/mypapers/dcnn_nips14.pdf">[Paper]</a>
  229. <ul>
  230. <li> Li Xu, Jimmy SJ. Ren, Ce Liu, Jiaya Jia, Deep Convolutional Neural Network for Image Deconvolution, NIPS, 2014.</li>
  231. </ul>
  232. </li>
  233. <li> Deep Edge-Aware Filter <a href="http://jmlr.org/proceedings/papers/v37/xub15.pdf">[Paper]</a>
  234. <ul>
  235. <li> Li Xu, Jimmy SJ. Ren, Qiong Yan, Renjie Liao, Jiaya Jia, Deep Edge-Aware Filters, ICML, 2015.</li>
  236. </ul>
  237. </li>
  238. <li>Computing the Stereo Matching Cost with a Convolutional Neural Network <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Zbontar_Computing_the_Stereo_2015_CVPR_paper.pdf">[Paper]</a>
  239. <ul>
  240. <li> Jure Žbontar, Yann LeCun, Computing the Stereo Matching Cost with a Convolutional Neural Network, CVPR, 2015.</li>
  241. </ul>
  242. </li>
  243. </ul>
  244. <h3>
  245. <a id="edge-detection" class="anchor" href="#edge-detection" aria-hidden="true"><span class="octicon octicon-link"></span></a>Edge Detection</h3>
  246. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8452371/93ca6f7e-2025-11e5-90f2-d428fd5ff7ac.PNG" alt="edge_detection">
  247. (from Gedas Bertasius, Jianbo Shi, Lorenzo Torresani, DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection, CVPR, 2015.)</p>
  248. <ul>
  249. <li>Holistically-Nested Edge Detection <a href="http://arxiv.org/pdf/1504.06375">[Paper]</a>
  250. <ul>
  251. <li>Saining Xie, Zhuowen Tu, Holistically-Nested Edge Detection, arXiv:1504.06375.</li>
  252. </ul>
  253. </li>
  254. <li>DeepEdge <a href="http://arxiv.org/pdf/1412.1123">[Paper]</a>
  255. <ul>
  256. <li>Gedas Bertasius, Jianbo Shi, Lorenzo Torresani, DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection, CVPR, 2015.</li>
  257. </ul>
  258. </li>
  259. <li>DeepContour <a href="http://mc.eistar.net/UpLoadFiles/Papers/DeepContour_cvpr15.pdf">[Paper]</a>
  260. <ul>
  261. <li>Wei Shen, Xinggang Wang, Yan Wang, Xiang Bai, Zhijiang Zhang, DeepContour: A Deep Convolutional Feature Learned by Positive-Sharing Loss for Contour Detection, CVPR, 2015.</li>
  262. </ul>
  263. </li>
  264. </ul>
  265. <h3>
  266. <a id="semantic-segmentation" class="anchor" href="#semantic-segmentation" aria-hidden="true"><span class="octicon octicon-link"></span></a>Semantic Segmentation</h3>
  267. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8452076/0ba8340c-2023-11e5-88bc-bebf4509b6bb.PNG" alt="semantic_segmantation">
  268. (from Jifeng Dai, Kaiming He, Jian Sun, BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation, arXiv:1503.01640.)</p>
  269. <ul>
  270. <li>PASCAL VOC2012 Challenge Leaderboard (02 Dec. 2015)
  271. <img src="https://cloud.githubusercontent.com/assets/7778428/11527440/5724d2bc-9924-11e5-9614-01b863629af3.png" alt="VOC2012_top_rankings">
  272. (from PASCAL VOC2012 <a href="http://host.robots.ox.ac.uk:8080/leaderboard/displaylb.php?challengeid=11&amp;compid=6">leaderboards</a>)</li>
  273. <li>Adelaide
  274. <ul>
  275. <li>Guosheng Lin, Chunhua Shen, Ian Reid, Anton van dan Hengel, Efficient piecewise training of deep structured models for semantic segmentation, arXiv:1504.01013. <a href="http://arxiv.org/pdf/1504.01013">[Paper]</a> (1st ranked in VOC2012)</li>
  276. <li>Guosheng Lin, Chunhua Shen, Ian Reid, Anton van den Hengel, Deeply Learning the Messages in Message Passing Inference, arXiv:1508.02108. <a href="http://arxiv.org/pdf/1506.02108">[Paper]</a> (4th ranked in VOC2012)</li>
  277. </ul>
  278. </li>
  279. <li>Deep Parsing Network (DPN)
  280. <ul>
  281. <li>Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang, Semantic Image Segmentation via Deep Parsing Network, arXiv:1509.02634 / ICCV 2015 <a href="http://arxiv.org/pdf/1509.02634.pdf">[Paper]</a> (2nd ranked in VOC 2012)</li>
  282. </ul>
  283. </li>
  284. <li>CentraleSuperBoundaries, INRIA <a href="http://arxiv.org/pdf/1511.07386">[Paper]</a>
  285. <ul>
  286. <li>Iasonas Kokkinos, Surpassing Humans in Boundary Detection using Deep Learning, arXiv:1411.07386 (4th ranked in VOC 2012)</li>
  287. </ul>
  288. </li>
  289. <li>BoxSup <a href="http://arxiv.org/pdf/1503.01640">[Paper]</a>
  290. <ul>
  291. <li>Jifeng Dai, Kaiming He, Jian Sun, BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation, arXiv:1503.01640. (6th ranked in VOC2012)</li>
  292. </ul>
  293. </li>
  294. <li>POSTECH
  295. <ul>
  296. <li>Hyeonwoo Noh, Seunghoon Hong, Bohyung Han, Learning Deconvolution Network for Semantic Segmentation, arXiv:1505.04366. <a href="http://arxiv.org/pdf/1505.04366">[Paper]</a> (7th ranked in VOC2012)</li>
  297. <li>Seunghoon Hong, Hyeonwoo Noh, Bohyung Han, Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation, arXiv:1506.04924. <a href="http://arxiv.org/pdf/1506.04924">[Paper]</a>
  298. </li>
  299. </ul>
  300. </li>
  301. <li>Conditional Random Fields as Recurrent Neural Networks <a href="http://arxiv.org/pdf/1502.03240">[Paper]</a>
  302. <ul>
  303. <li>Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes, Vibhav Vineet, Zhizhong Su, Dalong Du, Chang Huang, Philip H. S. Torr, Conditional Random Fields as Recurrent Neural Networks, arXiv:1502.03240. (8th ranked in VOC2012)</li>
  304. </ul>
  305. </li>
  306. <li>DeepLab
  307. <ul>
  308. <li> Liang-Chieh Chen, George Papandreou, Kevin Murphy, Alan L. Yuille, Weakly-and semi-supervised learning of a DCNN for semantic image segmentation, arXiv:1502.02734. <a href="http://arxiv.org/pdf/1502.02734">[Paper]</a> (9th ranked in VOC2012)</li>
  309. </ul>
  310. </li>
  311. <li>Zoom-out <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Mostajabi_Feedforward_Semantic_Segmentation_2015_CVPR_paper.pdf">[Paper]</a>
  312. <ul>
  313. <li>Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich, Feedforward Semantic Segmentation With Zoom-Out Features, CVPR, 2015</li>
  314. </ul>
  315. </li>
  316. <li>Joint Calibration <a href="http://arxiv.org/pdf/1507.01581">[Paper]</a>
  317. <ul>
  318. <li>Holger Caesar, Jasper Uijlings, Vittorio Ferrari, Joint Calibration for Semantic Segmentation, arXiv:1507.01581.</li>
  319. </ul>
  320. </li>
  321. <li>Fully Convolutional Networks for Semantic Segmentation <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Long_Fully_Convolutional_Networks_2015_CVPR_paper.pdf">[Paper-CVPR15]</a> <a href="http://arxiv.org/pdf/1411.4038">[Paper-arXiv15]</a>
  322. <ul>
  323. <li>Jonathan Long, Evan Shelhamer, Trevor Darrell, Fully Convolutional Networks for Semantic Segmentation, CVPR, 2015.</li>
  324. </ul>
  325. </li>
  326. <li>Hypercolumn <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Hariharan_Hypercolumns_for_Object_2015_CVPR_paper.pdf">[Paper]</a>
  327. <ul>
  328. <li>Bharath Hariharan, Pablo Arbelaez, Ross Girshick, Jitendra Malik, Hypercolumns for Object Segmentation and Fine-Grained Localization, CVPR, 2015.</li>
  329. </ul>
  330. </li>
  331. <li>Deep Hierarchical Parsing
  332. <ul>
  333. <li>Abhishek Sharma, Oncel Tuzel, David W. Jacobs, Deep Hierarchical Parsing for Semantic Segmentation, CVPR, 2015. <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Sharma_Deep_Hierarchical_Parsing_2015_CVPR_paper.pdf">[Paper]</a>
  334. </li>
  335. </ul>
  336. </li>
  337. <li>Learning Hierarchical Features for Scene Labeling <a href="http://yann.lecun.com/exdb/publis/pdf/farabet-icml-12.pdf">[Paper-ICML12]</a> <a href="http://yann.lecun.com/exdb/publis/pdf/farabet-pami-13.pdf">[Paper-PAMI13]</a>
  338. <ul>
  339. <li>Clement Farabet, Camille Couprie, Laurent Najman, Yann LeCun, Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers, ICML, 2012.</li>
  340. <li>Clement Farabet, Camille Couprie, Laurent Najman, Yann LeCun, Learning Hierarchical Features for Scene Labeling, PAMI, 2013.</li>
  341. </ul>
  342. </li>
  343. <li>University of Cambridge <a href="http://mi.eng.cam.ac.uk/projects/segnet/">[Web]</a>
  344. <ul>
  345. <li>Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation." arXiv preprint arXiv:1511.00561, 2015. <a href="http://arxiv.org/abs/1511.00561">[Paper]</a>
  346. </li>
  347. <li>Alex Kendall, Vijay Badrinarayanan and Roberto Cipolla "Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding." arXiv preprint arXiv:1511.02680, 2015. <a href="http://arxiv.org/abs/1511.00561">[Paper]</a>
  348. </li>
  349. </ul>
  350. </li>
  351. </ul>
  352. <h3>
  353. <a id="visual-attention-and-saliency" class="anchor" href="#visual-attention-and-saliency" aria-hidden="true"><span class="octicon octicon-link"></span></a>Visual Attention and Saliency</h3>
  354. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8492362/7ec65b88-2183-11e5-978f-017e45ddba32.png" alt="saliency">
  355. (from Nian Liu, Junwei Han, Dingwen Zhang, Shifeng Wen, Tianming Liu, Predicting Eye Fixations using Convolutional Neural Networks, CVPR, 2015.)</p>
  356. <ul>
  357. <li>Mr-CNN <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Liu_Predicting_Eye_Fixations_2015_CVPR_paper.pdf">[Paper]</a>
  358. <ul>
  359. <li>Nian Liu, Junwei Han, Dingwen Zhang, Shifeng Wen, Tianming Liu, Predicting Eye Fixations using Convolutional Neural Networks, CVPR, 2015.</li>
  360. </ul>
  361. </li>
  362. <li>Learning a Sequential Search for Landmarks <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Singh_Learning_a_Sequential_2015_CVPR_paper.pdf">[Paper]</a>
  363. <ul>
  364. <li>Saurabh Singh, Derek Hoiem, David Forsyth, Learning a Sequential Search for Landmarks, CVPR, 2015.</li>
  365. </ul>
  366. </li>
  367. <li>Multiple Object Recognition with Visual Attention <a href="http://arxiv.org/pdf/1412.7755.pdf">[Paper]</a>
  368. <ul>
  369. <li>Jimmy Lei Ba, Volodymyr Mnih, Koray Kavukcuoglu, Multiple Object Recognition with Visual Attention, ICLR, 2015.</li>
  370. </ul>
  371. </li>
  372. <li>Recurrent Models of Visual Attention <a href="http://papers.nips.cc/paper/5542-recurrent-models-of-visual-attention.pdf">[Paper]</a>
  373. <ul>
  374. <li>Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu, Recurrent Models of Visual Attention, NIPS, 2014.</li>
  375. </ul>
  376. </li>
  377. </ul>
  378. <h3>
  379. <a id="object-recognition" class="anchor" href="#object-recognition" aria-hidden="true"><span class="octicon octicon-link"></span></a>Object Recognition</h3>
  380. <ul>
  381. <li>Weakly-supervised learning with convolutional neural networks <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Oquab_Is_Object_Localization_2015_CVPR_paper.pdf">[Paper]</a>
  382. <ul>
  383. <li>Maxime Oquab, Leon Bottou, Ivan Laptev, Josef Sivic, Is object localization for free? – Weakly-supervised learning with convolutional neural networks, CVPR, 2015.</li>
  384. </ul>
  385. </li>
  386. <li>FV-CNN <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Cimpoi_Deep_Filter_Banks_2015_CVPR_paper.pdf">[Paper]</a>
  387. <ul>
  388. <li>Mircea Cimpoi, Subhransu Maji, Andrea Vedaldi, Deep Filter Banks for Texture Recognition and Segmentation, CVPR, 2015.</li>
  389. </ul>
  390. </li>
  391. </ul>
  392. <h3>
  393. <a id="understanding-cnn" class="anchor" href="#understanding-cnn" aria-hidden="true"><span class="octicon octicon-link"></span></a>Understanding CNN</h3>
  394. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8452083/1aaa0066-2023-11e5-800b-2248ead51584.PNG" alt="understanding">
  395. (from Aravindh Mahendran, Andrea Vedaldi, Understanding Deep Image Representations by Inverting Them, CVPR, 2015.)</p>
  396. <ul>
  397. <li>Equivariance and Equivalence of Representations <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Lenc_Understanding_Image_Representations_2015_CVPR_paper.pdf">[Paper]</a>
  398. <ul>
  399. <li>Karel Lenc, Andrea Vedaldi, Understanding image representations by measuring their equivariance and equivalence, CVPR, 2015.</li>
  400. </ul>
  401. </li>
  402. <li>Deep Neural Networks Are Easily Fooled <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Nguyen_Deep_Neural_Networks_2015_CVPR_paper.pdf">[Paper]</a>
  403. <ul>
  404. <li>Anh Nguyen, Jason Yosinski, Jeff Clune, Deep Neural Networks are Easily Fooled:High Confidence Predictions for Unrecognizable Images, CVPR, 2015.</li>
  405. </ul>
  406. </li>
  407. <li>Understanding Deep Image Representations by Inverting Them <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Mahendran_Understanding_Deep_Image_2015_CVPR_paper.pdf">[Paper]</a>
  408. <ul>
  409. <li>Aravindh Mahendran, Andrea Vedaldi, Understanding Deep Image Representations by Inverting Them, CVPR, 2015.</li>
  410. </ul>
  411. </li>
  412. <li>Object Detectors Emerge in Deep Scene CNNs <a href="http://arxiv.org/abs/1412.6856">[Paper]</a>
  413. <ul>
  414. <li>Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba, Object Detectors Emerge in Deep Scene CNNs, ICLR, 2015.</li>
  415. </ul>
  416. </li>
  417. <li>Inverting Convolutional Networks with Convolutional Networks
  418. <ul>
  419. <li>Alexey Dosovitskiy, Thomas Brox, Inverting Convolutional Networks with Convolutional Networks, arXiv, 2015. <a href="http://arxiv.org/abs/1506.02753">[Paper]</a>
  420. </li>
  421. </ul>
  422. </li>
  423. <li>Visualizing and Understanding CNN
  424. <ul>
  425. <li>Matthrew Zeiler, Rob Fergus, Visualizing and Understanding Convolutional Networks, ECCV, 2014. <a href="https://www.cs.nyu.edu/%7Efergus/papers/zeilerECCV2014.pdf">[Paper]</a>
  426. </li>
  427. </ul>
  428. </li>
  429. </ul>
  430. <h3>
  431. <a id="image-and-language" class="anchor" href="#image-and-language" aria-hidden="true"><span class="octicon octicon-link"></span></a>Image and Language</h3>
  432. <h4>
  433. <a id="image-captioning" class="anchor" href="#image-captioning" aria-hidden="true"><span class="octicon octicon-link"></span></a>Image Captioning</h4>
  434. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8452051/e8f81030-2022-11e5-85db-c68e7d8251ce.PNG" alt="image_captioning">
  435. (from Andrej Karpathy, Li Fei-Fei, Deep Visual-Semantic Alignments for Generating Image Description, CVPR, 2015.)</p>
  436. <ul>
  437. <li>UCLA / Baidu <a href="http://arxiv.org/pdf/1410.1090">[Paper]</a>
  438. <ul>
  439. <li>Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, Alan L. Yuille, Explain Images with Multimodal Recurrent Neural Networks, arXiv:1410.1090.</li>
  440. </ul>
  441. </li>
  442. <li>Toronto <a href="http://arxiv.org/pdf/1411.2539">[Paper]</a>
  443. <ul>
  444. <li>Ryan Kiros, Ruslan Salakhutdinov, Richard S. Zemel, Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models, arXiv:1411.2539.</li>
  445. </ul>
  446. </li>
  447. <li>Berkeley <a href="http://arxiv.org/pdf/1411.4389">[Paper]</a>
  448. <ul>
  449. <li>Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell, Long-term Recurrent Convolutional Networks for Visual Recognition and Description, arXiv:1411.4389.</li>
  450. </ul>
  451. </li>
  452. <li>Google <a href="http://arxiv.org/pdf/1411.4555">[Paper]</a>
  453. <ul>
  454. <li>Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan, Show and Tell: A Neural Image Caption Generator, arXiv:1411.4555.</li>
  455. </ul>
  456. </li>
  457. <li>Stanford <a href="http://cs.stanford.edu/people/karpathy/deepimagesent/">[Web]</a> <a href="http://cs.stanford.edu/people/karpathy/cvpr2015.pdf">[Paper]</a>
  458. <ul>
  459. <li>Andrej Karpathy, Li Fei-Fei, Deep Visual-Semantic Alignments for Generating Image Description, CVPR, 2015.</li>
  460. </ul>
  461. </li>
  462. <li>UML / UT <a href="http://arxiv.org/pdf/1412.4729">[Paper]</a>
  463. <ul>
  464. <li>Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, Kate Saenko, Translating Videos to Natural Language Using Deep Recurrent Neural Networks, NAACL-HLT, 2015.</li>
  465. </ul>
  466. </li>
  467. <li>CMU / Microsoft <a href="http://arxiv.org/pdf/1411.5654">[Paper-arXiv]</a> <a href="http://www.cs.cmu.edu/%7Exinleic/papers/cvpr15_rnn.pdf">[Paper-CVPR]</a>
  468. <ul>
  469. <li>Xinlei Chen, C. Lawrence Zitnick, Learning a Recurrent Visual Representation for Image Caption Generation, arXiv:1411.5654.</li>
  470. <li>Xinlei Chen, C. Lawrence Zitnick, Mind’s Eye: A Recurrent Visual Representation for Image Caption Generation, CVPR 2015</li>
  471. </ul>
  472. </li>
  473. <li>Microsoft <a href="http://arxiv.org/pdf/1411.4952">[Paper]</a>
  474. <ul>
  475. <li>Hao Fang, Saurabh Gupta, Forrest Iandola, Rupesh Srivastava, Li Deng, Piotr Dollár, Jianfeng Gao, Xiaodong He, Margaret Mitchell, John C. Platt, C. Lawrence Zitnick, Geoffrey Zweig, From Captions to Visual Concepts and Back, CVPR, 2015.</li>
  476. </ul>
  477. </li>
  478. <li>Univ. Montreal / Univ. Toronto [<a href="http://kelvinxu.github.io/projects/capgen.html">Web</a>] [<a href="http://www.cs.toronto.edu/%7Ezemel/documents/captionAttn.pdf">Paper</a>]
  479. <ul>
  480. <li>Kelvin Xu, Jimmy Lei Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S. Zemel, Yoshua Bengio, Show, Attend, and Tell: Neural Image Caption Generation with Visual Attention, arXiv:1502.03044 / ICML 2015</li>
  481. </ul>
  482. </li>
  483. <li>Idiap / EPFL / Facebook [<a href="http://arxiv.org/pdf/1502.03671">Paper</a>]
  484. <ul>
  485. <li>Remi Lebret, Pedro O. Pinheiro, Ronan Collobert, Phrase-based Image Captioning, arXiv:1502.03671 / ICML 2015</li>
  486. </ul>
  487. </li>
  488. <li>UCLA / Baidu [<a href="http://arxiv.org/pdf/1504.06692">Paper</a>]
  489. <ul>
  490. <li>Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, Zhiheng Huang, Alan L. Yuille, Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images, arXiv:1504.06692</li>
  491. </ul>
  492. </li>
  493. <li>MS + Berkeley
  494. <ul>
  495. <li>Jacob Devlin, Saurabh Gupta, Ross Girshick, Margaret Mitchell, C. Lawrence Zitnick, Exploring Nearest Neighbor Approaches for Image Captioning, arXiv:1505.04467 [<a href="http://arxiv.org/pdf/1505.04467.pdf">Paper</a>]</li>
  496. <li>Jacob Devlin, Hao Cheng, Hao Fang, Saurabh Gupta, Li Deng, Xiaodong He, Geoffrey Zweig, Margaret Mitchell, Language Models for Image Captioning: The Quirks and What Works, arXiv:1505.01809 [<a href="http://arxiv.org/pdf/1505.01809.pdf">Paper</a>]</li>
  497. </ul>
  498. </li>
  499. <li>Adelaide [<a href="http://arxiv.org/pdf/1506.01144.pdf">Paper</a>]
  500. <ul>
  501. <li>Qi Wu, Chunhua Shen, Anton van den Hengel, Lingqiao Liu, Anthony Dick, Image Captioning with an Intermediate Attributes Layer, arXiv:1506.01144</li>
  502. </ul>
  503. </li>
  504. <li>Tilburg [<a href="http://arxiv.org/pdf/1506.03694.pdf">Paper</a>]
  505. <ul>
  506. <li>Grzegorz Chrupala, Akos Kadar, Afra Alishahi, Learning language through pictures, arXiv:1506.03694</li>
  507. </ul>
  508. </li>
  509. <li>Univ. Montreal [<a href="http://arxiv.org/pdf/1507.01053.pdf">Paper</a>]
  510. <ul>
  511. <li>Kyunghyun Cho, Aaron Courville, Yoshua Bengio, Describing Multimedia Content using Attention-based Encoder-Decoder Networks, arXiv:1507.01053</li>
  512. </ul>
  513. </li>
  514. <li>Cornell [<a href="http://arxiv.org/pdf/1508.02091.pdf">Paper</a>]
  515. <ul>
  516. <li>Jack Hessel, Nicolas Savva, Michael J. Wilber, Image Representations and New Domains in Neural Image Captioning, arXiv:1508.02091</li>
  517. </ul>
  518. </li>
  519. </ul>
  520. <h4>
  521. <a id="video-captioning" class="anchor" href="#video-captioning" aria-hidden="true"><span class="octicon octicon-link"></span></a>Video Captioning</h4>
  522. <ul>
  523. <li>Berkeley <a href="http://jeffdonahue.com/lrcn/">[Web]</a> <a href="http://arxiv.org/pdf/1411.4389.pdf">[Paper]</a>
  524. <ul>
  525. <li>Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell, Long-term Recurrent Convolutional Networks for Visual Recognition and Description, CVPR, 2015.</li>
  526. </ul>
  527. </li>
  528. <li>UT / UML / Berkeley <a href="http://arxiv.org/pdf/1412.4729">[Paper]</a>
  529. <ul>
  530. <li>Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, Kate Saenko, Translating Videos to Natural Language Using Deep Recurrent Neural Networks, arXiv:1412.4729.</li>
  531. </ul>
  532. </li>
  533. <li>Microsoft <a href="http://arxiv.org/pdf/1505.01861">[Paper]</a>
  534. <ul>
  535. <li>Yingwei Pan, Tao Mei, Ting Yao, Houqiang Li, Yong Rui, Joint Modeling Embedding and Translation to Bridge Video and Language, arXiv:1505.01861.</li>
  536. </ul>
  537. </li>
  538. <li>UT / Berkeley / UML <a href="http://arxiv.org/pdf/1505.00487">[Paper]</a>
  539. <ul>
  540. <li>Subhashini Venugopalan, Marcus Rohrbach, Jeff Donahue, Raymond Mooney, Trevor Darrell, Kate Saenko, Sequence to Sequence--Video to Text, arXiv:1505.00487.</li>
  541. </ul>
  542. </li>
  543. <li>Univ. Montreal / Univ. Sherbrooke [<a href="http://arxiv.org/pdf/1502.08029.pdf">Paper</a>]
  544. <ul>
  545. <li>Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, Aaron Courville, Describing Videos by Exploiting Temporal Structure, arXiv:1502.08029</li>
  546. </ul>
  547. </li>
  548. <li>MPI / Berkeley [<a href="http://arxiv.org/pdf/1506.01698.pdf">Paper</a>]
  549. <ul>
  550. <li>Anna Rohrbach, Marcus Rohrbach, Bernt Schiele, The Long-Short Story of Movie Description, arXiv:1506.01698</li>
  551. </ul>
  552. </li>
  553. <li>Univ. Toronto / MIT [<a href="http://arxiv.org/pdf/1506.06724.pdf">Paper</a>]
  554. <ul>
  555. <li>Yukun Zhu, Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler, Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books, arXiv:1506.06724</li>
  556. </ul>
  557. </li>
  558. <li>Univ. Montreal [<a href="http://arxiv.org/pdf/1507.01053.pdf">Paper</a>]
  559. <ul>
  560. <li>Kyunghyun Cho, Aaron Courville, Yoshua Bengio, Describing Multimedia Content using Attention-based Encoder-Decoder Networks, arXiv:1507.01053</li>
  561. </ul>
  562. </li>
  563. </ul>
  564. <h4>
  565. <a id="question-answering" class="anchor" href="#question-answering" aria-hidden="true"><span class="octicon octicon-link"></span></a>Question Answering</h4>
  566. <p><img src="https://cloud.githubusercontent.com/assets/5226447/8452068/ffe7b1f6-2022-11e5-87ab-4f6d4696c220.PNG" alt="question_answering">
  567. (from Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh, VQA: Visual Question Answering, CVPR, 2015 SUNw:Scene Understanding workshop)</p>
  568. <ul>
  569. <li>Virginia Tech / MSR <a href="http://www.visualqa.org/">[Web]</a> <a href="http://arxiv.org/pdf/1505.00468">[Paper]</a>
  570. <ul>
  571. <li>Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh, VQA: Visual Question Answering, CVPR, 2015 SUNw:Scene Understanding workshop.</li>
  572. </ul>
  573. </li>
  574. <li>MPI / Berkeley <a href="https://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/research/vision-and-language/visual-turing-challenge/">[Web]</a> <a href="http://arxiv.org/pdf/1505.01121">[Paper]</a>
  575. <ul>
  576. <li>Mateusz Malinowski, Marcus Rohrbach, Mario Fritz, Ask Your Neurons: A Neural-based Approach to Answering Questions about Images, arXiv:1505.01121.</li>
  577. </ul>
  578. </li>
  579. <li>Toronto <a href="http://arxiv.org/pdf/1505.02074">[Paper]</a> <a href="http://www.cs.toronto.edu/%7Emren/imageqa/data/cocoqa/">[Dataset]</a>
  580. <ul>
  581. <li>Mengye Ren, Ryan Kiros, Richard Zemel, Image Question Answering: A Visual Semantic Embedding Model and a New Dataset, arXiv:1505.02074 / ICML 2015 deep learning workshop.</li>
  582. </ul>
  583. </li>
  584. <li>Baidu / UCLA <a href="http://arxiv.org/pdf/1505.05612">[Paper]</a> <a href="">[Dataset]</a>
  585. <ul>
  586. <li>Hauyuan Gao, Junhua Mao, Jie Zhou, Zhiheng Huang, Lei Wang, Wei Xu, Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering, arXiv:1505.05612.</li>
  587. </ul>
  588. </li>
  589. </ul>
  590. <h3>
  591. <a id="other-topics" class="anchor" href="#other-topics" aria-hidden="true"><span class="octicon octicon-link"></span></a>Other Topics</h3>
  592. <ul>
  593. <li>Surface Normal Estimation <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Wang_Designing_Deep_Networks_2015_CVPR_paper.pdf">[Paper]</a>
  594. <ul>
  595. <li>Xiaolong Wang, David F. Fouhey, Abhinav Gupta, Designing Deep Networks for Surface Normal Estimation, CVPR, 2015.</li>
  596. </ul>
  597. </li>
  598. <li>Action Detection <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Gkioxari_Finding_Action_Tubes_2015_CVPR_paper.pdf">[Paper]</a>
  599. <ul>
  600. <li>Georgia Gkioxari, Jitendra Malik, Finding Action Tubes, CVPR, 2015.</li>
  601. </ul>
  602. </li>
  603. <li>Crowd Counting <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Zhang_Cross-Scene_Crowd_Counting_2015_CVPR_paper.pdf">[Paper]</a>
  604. <ul>
  605. <li>Cong Zhang, Hongsheng Li, Xiaogang Wang, Xiaokang Yang, Cross-scene Crowd Counting via Deep Convolutional Neural Networks, CVPR, 2015.</li>
  606. </ul>
  607. </li>
  608. <li>3D Shape Retrieval <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Wang_Sketch-Based_3D_Shape_2015_CVPR_paper.pdf">[Paper]</a>
  609. <ul>
  610. <li>Fang Wang, Le Kang, Yi Li, Sketch-based 3D Shape Retrieval using Convolutional Neural Networks, CVPR, 2015.</li>
  611. </ul>
  612. </li>
  613. <li>Generate image <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Dosovitskiy_Learning_to_Generate_2015_CVPR_paper.pdf">[Paper]</a>
  614. <ul>
  615. <li>Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox, Learning to Generate Chairs with Convolutional Neural Networks, CVPR, 2015.</li>
  616. </ul>
  617. </li>
  618. <li>Generate Image with Adversarial Network
  619. <ul>
  620. <li>Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, Generative Adversarial Networks, NIPS, 2014. <a href="http://arxiv.org/abs/1406.2661">[Paper]</a>
  621. </li>
  622. <li>Emily Denton, Soumith Chintala, Arthur Szlam, Rob Fergus, Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks, NIPS, 2015. <a href="http://arxiv.org/abs/1506.05751">[Paper]</a>
  623. </li>
  624. </ul>
  625. </li>
  626. <li>Artistic Style <a href="http://arxiv.org/pdf/1506.04878v3">[Paper]</a> <a href="https://github.com/jcjohnson/neural-style">[Code]</a>
  627. <ul>
  628. <li>Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, A Neural Algorithm of Artistic Style.</li>
  629. </ul>
  630. </li>
  631. <li>Human Gaze Estimation
  632. <ul>
  633. <li>Xucong Zhang, Yusuke Sugano, Mario Fritz, Andreas Bulling, Appearance-Based Gaze Estimation in the Wild, CVPR, 2015. <a href="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Zhang_Appearance-Based_Gaze_Estimation_2015_CVPR_paper.pdf">[Paper]</a> <a href="https://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/research/gaze-based-human-computer-interaction/appearance-based-gaze-estimation-in-the-wild/">[Website]</a>
  634. </li>
  635. </ul>
  636. </li>
  637. </ul>
  638. <h2>
  639. <a id="courses" class="anchor" href="#courses" aria-hidden="true"><span class="octicon octicon-link"></span></a>Courses</h2>
  640. <ul>
  641. <li>Deep Vision
  642. <ul>
  643. <li>[Stanford] <a href="http://cs231n.stanford.edu/">CS231n: Convolutional Neural Networks for Visual Recognition</a>
  644. </li>
  645. <li>[CUHK] <a href="https://piazza.com/cuhk.edu.hk/spring2015/eleg5040/home">ELEG 5040: Advanced Topics in Signal Processing(Introduction to Deep Learning)</a>
  646. </li>
  647. </ul>
  648. </li>
  649. <li>More Deep Learning
  650. <ul>
  651. <li>[Stanford] <a href="http://cs224d.stanford.edu/">CS224d: Deep Learning for Natural Language Processing</a>
  652. </li>
  653. <li>[Oxford] <a href="https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearning/">Deep Learning by Prof. Nando de Freitas</a>
  654. </li>
  655. <li>[NYU] <a href="http://cilvr.cs.nyu.edu/doku.php?id=courses:deeplearning2014:start">Deep Learning by Prof. Yann LeCun</a>
  656. </li>
  657. </ul>
  658. </li>
  659. </ul>
  660. <h2>
  661. <a id="books" class="anchor" href="#books" aria-hidden="true"><span class="octicon octicon-link"></span></a>Books</h2>
  662. <ul>
  663. <li>Free Online Books
  664. <ul>
  665. <li><a href="http://www.iro.umontreal.ca/%7Ebengioy/dlbook/">Deep Learning by Yoshua Bengio, Ian Goodfellow and Aaron Courville</a></li>
  666. <li><a href="http://neuralnetworksanddeeplearning.com/">Neural Networks and Deep Learning by Michael Nielsen</a></li>
  667. <li><a href="http://deeplearning.net/tutorial/deeplearning.pdf">Deep Learning Tutorial by LISA lab, University of Montreal</a></li>
  668. </ul>
  669. </li>
  670. </ul>
  671. <h2>
  672. <a id="videos" class="anchor" href="#videos" aria-hidden="true"><span class="octicon octicon-link"></span></a>Videos</h2>
  673. <ul>
  674. <li>Talks
  675. <ul>
  676. <li><a href="https://www.youtube.com/watch?v=n1ViNeWhC24">Deep Learning, Self-Taught Learning and Unsupervised Feature Learning By Andrew Ng</a></li>
  677. <li> <a href="https://www.youtube.com/watch?v=sc-KbuZqGkI">Recent Developments in Deep Learning By Geoff Hinton</a>
  678. </li>
  679. <li> <a href="https://www.youtube.com/watch?v=sc-KbuZqGkI">The Unreasonable Effectiveness of Deep Learning by Yann LeCun</a>
  680. </li>
  681. <li><a href="https://www.youtube.com/watch?v=4xsVFLnHC_0">Deep Learning of Representations by Yoshua bengio</a></li>
  682. </ul>
  683. </li>
  684. <li>Courses
  685. <ul>
  686. <li><a href="http://www.computervisiontalks.com/tag/deep-learning-course/">Deep Learning Course – Nando de Freitas@Oxford</a></li>
  687. </ul>
  688. </li>
  689. </ul>
  690. <h2>
  691. <a id="software" class="anchor" href="#software" aria-hidden="true"><span class="octicon octicon-link"></span></a>Software</h2>
  692. <h3>
  693. <a id="framework" class="anchor" href="#framework" aria-hidden="true"><span class="octicon octicon-link"></span></a>Framework</h3>
  694. <ul>
  695. <li>Torch7: Deep learning library in Lua, used by Facebook and Google Deepmind <a href="http://torch.ch/">[Web]</a>
  696. </li>
  697. <li>Caffe: Deep learning framework by the BVLC <a href="http://caffe.berkeleyvision.org/">[Web]</a>
  698. </li>
  699. <li>Theano: Mathematical library in Python, maintained by LISA lab <a href="http://deeplearning.net/software/theano/">[Web]</a>
  700. <ul>
  701. <li>Theano-based deep learning libraries: <a href="http://deeplearning.net/software/pylearn2/">Pylearn2</a>, <a href="https://github.com/mila-udem/blocks">Blocks</a>, <a href="http://keras.io/">Keras</a>, <a href="https://github.com/Lasagne/Lasagne">Lasagne</a>
  702. </li>
  703. </ul>
  704. </li>
  705. <li>MatConvNet: CNNs for MATLAB <a href="http://www.vlfeat.org/matconvnet/">[Web]</a>
  706. </li>
  707. </ul>
  708. <h3>
  709. <a id="applications" class="anchor" href="#applications" aria-hidden="true"><span class="octicon octicon-link"></span></a>Applications</h3>
  710. <ul>
  711. <li>Adversarial Training
  712. <ul>
  713. <li>Code and hyperparameters for the paper "Generative Adversarial Networks" <a href="https://github.com/goodfeli/adversarial">[Web]</a>
  714. </li>
  715. </ul>
  716. </li>
  717. <li>Understanding and Visualizing
  718. <ul>
  719. <li>Source code for "Understanding Deep Image Representations by Inverting Them," CVPR, 2015. <a href="https://github.com/aravindhm/deep-goggle">[Web]</a>
  720. </li>
  721. </ul>
  722. </li>
  723. <li>Semantic Segmentation
  724. <ul>
  725. <li>Source code for the paper "Rich feature hierarchies for accurate object detection and semantic segmentation," CVPR, 2014. <a href="https://github.com/rbgirshick/rcnn">[Web]</a>
  726. </li>
  727. <li>Source code for the paper "Fully Convolutional Networks for Semantic Segmentation," CVPR, 2015. <a href="https://github.com/longjon/caffe/tree/future">[Web]</a>
  728. </li>
  729. </ul>
  730. </li>
  731. <li>Super-Resolution
  732. <ul>
  733. <li>Image Super-Resolution for Anime-Style-Art <a href="https://github.com/nagadomi/waifu2x">[Web]</a>
  734. </li>
  735. </ul>
  736. </li>
  737. <li>Edge Detection
  738. <ul>
  739. <li>Source code for the paper "DeepContour: A Deep Convolutional Feature Learned by Positive-Sharing Loss for Contour Detection," CVPR, 2015. <a href="https://github.com/shenwei1231/DeepContour">[Web]</a>
  740. </li>
  741. </ul>
  742. </li>
  743. </ul>
  744. <h2>
  745. <a id="tutorials" class="anchor" href="#tutorials" aria-hidden="true"><span class="octicon octicon-link"></span></a>Tutorials</h2>
  746. <ul>
  747. <li>[CVPR 2014] <a href="https://sites.google.com/site/deeplearningcvpr2014/">Tutorial on Deep Learning in Computer Vision</a>
  748. </li>
  749. <li>[CVPR 2015] <a href="http://torch.ch/docs/cvpr15.html">Applied Deep Learning for Computer Vision with Torch</a>
  750. </li>
  751. </ul>
  752. <h2>
  753. <a id="blogs" class="anchor" href="#blogs" aria-hidden="true"><span class="octicon octicon-link"></span></a>Blogs</h2>
  754. <ul>
  755. <li><a href="http://www.computervisionblog.com/2015/06/deep-down-rabbit-hole-cvpr-2015-and.html">Deep down the rabbit hole: CVPR 2015 and beyond@Tombone's Computer Vision Blog</a></li>
  756. <li><a href="http://zoyathinks.blogspot.kr/2015/06/cvpr-recap-and-where-were-going.html">CVPR recap and where we're going@Zoya Bylinskii (MIT PhD Student)'s Blog</a></li>
  757. <li><a href="http://www.wired.com/2015/06/facebook-googles-fake-brains-spawn-new-visual-reality/">Facebook's AI Painting@Wired</a></li>
  758. <li><a href="http://googleresearch.blogspot.kr/2015/06/inceptionism-going-deeper-into-neural.html">Inceptionism: Going Deeper into Neural Networks@Google Research</a></li>
  759. </ul>
  760. </section>
  761. </div>
  762. <footer>
  763. <p>Project maintained by <a href="https://github.com/kjw0612">kjw0612</a></p>
  764. <p>Hosted on GitHub Pages &mdash; Theme by <a href="https://github.com/orderedlist">orderedlist</a></p>
  765. </footer>
  766. <!--[if !IE]><script>fixScale(document);</script><![endif]-->
  767. <script type="text/javascript">
  768. var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www.");
  769. document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E"));
  770. </script>
  771. <script type="text/javascript">
  772. try {
  773. var pageTracker = _gat._getTracker("UA-64569684-1");
  774. pageTracker._trackPageview();
  775. } catch(err) {}
  776. </script>
  777. </body>
  778. </html>