{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:11:37Z","timestamp":1781622697386,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61751307"],"award-info":[{"award-number":["61751307"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Youth Top-notch Talent Support Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/tmm.2018.2846411","type":"journal-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T18:42:13Z","timestamp":1528742533000},"page":"246-255","source":"Crossref","is-referenced-by-count":107,"title":["Sparse Coding Guided Spatiotemporal Feature Learning for Abnormal Event Detection in Large Videos"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0816-7975","authenticated-orcid":false,"given":"Wenqing","family":"Chu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3161-3566","authenticated-orcid":false,"given":"Hongyang","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6035-1502","authenticated-orcid":false,"given":"Chengwei","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-4065","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"641","article-title":"Energy-based localized anomaly detection in video surveillance","author":"vu","year":"0","journal-title":"Proc of the Pacific and Asia Conf on Knowledge Discovery and Data Mining"},{"key":"ref72","first-page":"189","article-title":"Abnormal event detection in videos using spatiotemporal autoencoder","author":"chong","year":"0","journal-title":"Proc Int Symp Neural Netw"},{"key":"ref71","article-title":"UCF101: A dataset of 101 human action classes from videos in the wild","author":"soomro","year":"2012","journal-title":"CRCV-TR-12-01"},{"key":"ref70","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.06.007"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2631881"},{"key":"ref33","first-page":"8-1","article-title":"Learning deep representations of appearance and motion for anomalous event detection","author":"xu","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref32","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref31","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref36","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2670780"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref62","first-page":"3755","article-title":"Online detection of abnormal events using incremental coding length.","author":"dutta","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2323014"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.147"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.315"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref67","first-page":"678","article-title":"Unsupervised visual representation learning by graph-based consistent constraints","author":"li","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.126"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214049"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995648"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995434"},{"key":"ref22","first-page":"334","article-title":"A discriminative framework for anomaly detection in large videos","author":"giorno","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/34.868677"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995524"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206771"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539882"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2233723"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2237023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206686"},{"key":"ref54","first-page":"28","article-title":"Unsupervised behavior-specific dictionary learning for abnormal event detection","author":"ren","year":"0","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247917"},{"key":"ref52","first-page":"2415","article-title":"Video parsing for abnormality detection","author":"anti?","year":"2011","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2635589"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0354-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.337"},{"key":"ref14","first-page":"488","article-title":"Interestingness prediction by robust learning to rank","author":"fu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.127"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005599"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2008.2012070"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2416555"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref6","first-page":"187","article-title":"Cats: Co-saliency activated tracklet selection for video co-localization","author":"jerripothula","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2616297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref7","article-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","author":"montes","year":"2016","journal-title":"1st NIPS Workshop on Large Scale Computer Vision Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206569"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2011.09.009"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70731"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70825"},{"key":"ref42","first-page":"110","article-title":"Learning semantic scene models by trajectory analysis","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/216"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995558"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206809"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8584144\/08379443.pdf?arnumber=8379443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:59:30Z","timestamp":1657745970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8379443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":74,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2846411","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}