{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:16:50Z","timestamp":1781781410142,"version":"3.54.5"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014036","name":"MURI","doi-asserted-by":"crossref","award":["N000141010933"],"award-info":[{"award-number":["N000141010933"]}],"id":[{"id":"10.13039\/100014036","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Google Research"},{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"NVIDIA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPUs"},{"DOI":"10.13039\/100006978","name":"University of California Berkeley","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006978","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2017,4,1]]},"DOI":"10.1109\/tpami.2016.2578328","type":"journal-article","created":{"date-parts":[[2016,6,8]],"date-time":"2016-06-08T18:17:41Z","timestamp":1465409861000},"page":"627-639","source":"Crossref","is-referenced-by-count":85,"title":["Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2309-4703","authenticated-orcid":false,"given":"Bharath","family":"Hariharan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Arbelaez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ross","family":"Girshick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126398"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298959"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref31","first-page":"237","article-title":"Reconstructive sparse code transfer for contour detection and semantic labeling","author":"maire","year":"2014","journal-title":"Asian Conf Computer Vision"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.465"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.208"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47967-8_8"},{"key":"ref35","first-page":"2758","article-title":"Flownet: Learning optical flow with convolutional networks","author":"fischer","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-55426-2_71"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF01421489"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref22","first-page":"328","article-title":"Multiscale combinatorial grouping","author":"arbel","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095851"},{"key":"ref23","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.7.000923"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00318371"},{"key":"ref50","first-page":"1871","article-title":"Liblinear: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.428"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref55","first-page":"168","article-title":"Detecting people using mutually consistent\n poselet activations","author":"bourdev","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref10","first-page":"25","article-title":"High accuracy optical flow estimation\n based on a theory for warping","author":"brox","year":"0","journal-title":"Proc 8th Eur Conf Comput Vis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"ref40","first-page":"3322","article-title":"Learning to localize detected objects","author":"dai","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248101"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995609"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.329"},{"key":"ref17","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks\n for visual recognition","author":"he","year":"0","journal-title":"Proc 8th Eur Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref19","article-title":"R-CNNs for pose estimation and action\n detection","author":"gkioxari","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"297","article-title":"Simultaneous detection and\n segmentation","author":"hariharan","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref8","first-page":"834","article-title":"Part-based R-CNNs for fine-grained\n category detection","author":"zhang","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref7","first-page":"1799","article-title":"Joint training of a convolutional\n network and a graphical model for human pose estimation","author":"tompson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.184"},{"key":"ref9","article-title":"Improved bird species recognition using\n pose normalized deep convolutional nets","volume":"1","author":"branson","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.458"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298788"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.215"},{"key":"ref42","first-page":"299","article-title":"Towards unified object detection and\n semantic segmentation","author":"dong","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.423"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"ref43","first-page":"430","article-title":"Semantic segmentation with\n second-order pooling","author":"carreira","year":"0","journal-title":"Proc 12th Eur Conf Comput Vision"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7870775\/07486965.pdf?arnumber=7486965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:08:20Z","timestamp":1642003700000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7486965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,1]]},"references-count":56,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2578328","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4,1]]}}}