{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:49:57Z","timestamp":1781974197158,"version":"3.54.5"},"reference-count":49,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/cvpr.2015.7299097","type":"proceedings-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T18:42:06Z","timestamp":1444934526000},"page":"4657-4666","source":"Crossref","is-referenced-by-count":201,"title":["Deeply learned attributes for crowded scene understanding"],"prefix":"10.1109","author":[{"given":"Jing","family":"Shao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaogang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383072"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.285"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126374"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995451"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref35","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383198"},{"key":"ref28","first-page":"145","article-title":"Modeling the shape of the scene: A holistic representation of the spatial envelope","volume":"42","author":"oliva","year":"2001","journal-title":"IJ CV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"ref29","article-title":"Deepid-net: multi-stage and deformable deep convolutional neural networks for object detection","author":"ouyang","year":"2014","journal-title":"arXiv preprint arXiv 1409 3505"},{"key":"ref2","article-title":"Floor fields for tracking in high density crowd scenes","author":"ali","year":"2008","journal-title":"ECCV"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.382977"},{"key":"ref20","article-title":"Learning to detect unseen object classes by between-class attribute trans-fer","author":"lampert","year":"2009","journal-title":"CVPR"},{"key":"ref22","article-title":"Scene segmentation for behaviour correlation","author":"li","year":"2008","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref24","article-title":"Multi-camera activity correlation analysis","author":"loy","year":"2009","journal-title":"CVPR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.356"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298971"},{"key":"ref12","first-page":"10","article-title":"What do we perceive in a glance of a real-world scene? Journal of vision","volume":"7","author":"fei-fei","year":"2007"},{"key":"ref13","article-title":"Attribute learning for understanding unstructured social activity","author":"fu","year":"0","journal-title":"ECCV 2012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459342"},{"key":"ref16","article-title":"Fully convolutional neural networks for crowd segmentation","author":"kang","year":"2014","journal-title":"arXiv preprint arXiv 1411 4464"},{"key":"ref17","article-title":"Yarge-scale video classification with convolutional neural networks","author":"karpathy","year":"2014","journal-title":"CVPR"},{"key":"ref18","article-title":"Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern mod-els","author":"kratz","year":"2009","journal-title":"CVPR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"ref4","article-title":"Automatic attribute discovery and characterization from noisy web data","author":"berg","year":"2010","journal-title":"ECCV"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.806"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.81.591"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.77.046113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70738"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.21"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0735-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.392"},{"key":"ref48","article-title":"Understanding collective crowd behaviors: Learning a mixture model of dynamic pedestrian-agents","author":"zhou","year":"2012","journal-title":"CVPR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300484"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"ref41","article-title":"LO regularized stationary time estimation for crowd group analysis","author":"yi","year":"2014","journal-title":"CVPR"},{"key":"ref44","article-title":"Coherent filtering: detecting coherent motions from crowd clutters","author":"zhou","year":"2012","journal-title":"ECCwjtcV"},{"key":"ref43","first-page":"1465","article-title":"Rotation-invariant image and video description with local binary pattern features","volume":"21","author":"zhao","year":"2012","journal-title":"TIP"}],"event":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Boston, MA, USA","start":{"date-parts":[[2015,6,7]]},"end":{"date-parts":[[2015,6,12]]}},"container-title":["2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7293313\/7298593\/07299097.pdf?arnumber=7299097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T17:42:21Z","timestamp":1490377341000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7299097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2015.7299097","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}