{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:48:11Z","timestamp":1777657691847,"version":"3.51.4"},"reference-count":63,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/cvpr.2018.00132","type":"proceedings-article","created":{"date-parts":[[2018,12,17]],"date-time":"2018-12-17T20:49:37Z","timestamp":1545079777000},"page":"1209-1218","source":"Crossref","is-referenced-by-count":984,"title":["COCO-Stuff: Thing and Stuff Classes in Context"],"prefix":"10.1109","author":[{"given":"Holger","family":"Caesar","sequence":"first","affiliation":[]},{"given":"Jasper","family":"Uijlings","sequence":"additional","affiliation":[]},{"given":"Vittorio","family":"Ferrari","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.404"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref33","first-page":"109","article-title":"Efficient inference in fully connected CRFs with gaussian edge potentials","author":"kr\u00e4henb\u00fchl","year":"2011","journal-title":"NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0202-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33885-4_30"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1609\/hcomp.v4i1.13288","article-title":"Click carving: Segmenting objects in video with point clicks","author":"jain","year":"2016","journal-title":"Proceedings of the Fourth AAAI Conference on Human Computation and Crowdsourcing"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.131"},{"key":"ref35","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.151"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299002"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139439"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248101"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref28","first-page":"1827","article-title":"Probabilistic joint image segmentation and labeling","author":"ion","year":"2011","journal-title":"NIPS"},{"key":"ref27","article-title":"Learning spatial context: Using stuff to find things","author":"heitz","year":"2008","journal-title":"ECCV"},{"key":"ref29","article-title":"Training deep networks with structured layers by matrix backpropagation","author":"ionescu","year":"2015","journal-title":"ICCV"},{"key":"ref2","first-page":"1","article-title":"On seeing stuff: The perception of materials by humans and machines","author":"adelson","year":"2001","journal-title":"SPIE Proceedings Series"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref22","article-title":"Video segmentation with superpixels","author":"galasso","year":"2012","journal-title":"ACCV"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-61750-7_36","article-title":"Finding pictures of objects in large collections of images","author":"forsyth","year":"1996","journal-title":"Int Workshop on Object Representations for Computer Vision"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459211"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Simultaneous detection and segmentation","author":"hariharan","year":"2014","journal-title":"ECCV"},{"key":"ref50","article-title":"Superparsing: Scalable nonparametric image parsing with superpixels","author":"tighe","year":"2010","journal-title":"ECCV"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.386"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref58","first-page":"1","article-title":"SUN database: Exploring a large collection of scene categories","author":"xiao","year":"2014","journal-title":"IJCV"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.10.013"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298788"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073478"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.479"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0574-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.477"},{"key":"ref11","article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","author":"chen","year":"2015","journal-title":"ICLRE"},{"key":"ref40","article-title":"Semiautomatic video object segmentation by advanced manipulation of segmentation hierarchies","author":"pont-tuset","year":"2015","journal-title":"International Workshop on Content-Based Multimedia Indexing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/300776.300778","article-title":"Reflectance and texture of real-world surfaces","volume":"18","author":"dana","year":"1999","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.122"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/2461912.2462002","article-title":"OpenSur-faces: A richly annotated catalog of surface appearance","author":"bell","year":"2013","journal-title":"SIGGRAPH"},{"key":"ref3","article-title":"What's the point: Semantic segmentation with point supervision","author":"bearman","year":"2016","journal-title":"ECCV"},{"key":"ref6","author":"brodatz","year":"1966","journal-title":"Textures A Photographic Album for Artists and Designers"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"ref8","article-title":"Region-based semantic segmentation with end-to-end training","author":"caesar","year":"2016","journal-title":"ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.05.005"},{"key":"ref46","article-title":"Texton-Boost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation","author":"shotton","year":"2006","journal-title":"ECCV"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.366"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref47","article-title":"Indoor segmentation and support inference from rgbd images","author":"silberman","year":"2012","journal-title":"ECCV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1186562.1015720"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"ref44","article-title":"Material perception: What can you see in a brief glance?","volume":"14","author":"sharan","year":"2014","journal-title":"Journal of Vision"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"}],"event":{"name":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Salt Lake City, UT, USA","start":{"date-parts":[[2018,6,18]]},"end":{"date-parts":[[2018,6,23]]}},"container-title":["2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8576498\/8578098\/08578230.pdf?arnumber=8578230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T03:14:28Z","timestamp":1694488468000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8578230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2018.00132","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}