{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T04:24:59Z","timestamp":1778991899639,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Laboratory Project of Publishing Science and Technology and Standards"},{"name":"National Press and Publication Administration - Key Laboratory of Augmented Reality Integrated Publishing","award":["BZ2021006"],"award-info":[{"award-number":["BZ2021006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3112814","type":"journal-article","created":{"date-parts":[[2021,9,16]],"date-time":"2021-09-16T20:07:26Z","timestamp":1631822846000},"page":"4067-4076","source":"Crossref","is-referenced-by-count":73,"title":["Contrastive Attention for Video Anomaly Detection"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5752-0128","authenticated-orcid":false,"given":"Shuning","family":"Chang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6291-0523","authenticated-orcid":false,"given":"Yanchao","family":"Li","sequence":"additional","affiliation":[{"name":"Pensees, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengmei","family":"Shen","sequence":"additional","affiliation":[{"name":"Pensees, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0064","authenticated-orcid":false,"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8455-1915","authenticated-orcid":false,"given":"Zhiying","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"358","article-title":"Claws: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection","author":"zaheer","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref33","first-page":"322","article-title":"Not only look, but also listen: Learning multimodal violence detection under weak supervision","author":"wu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2953814"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","article-title":"Temporal segment networks for action recognition in videos","volume":"41","author":"wang","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102722"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref36","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539882"},{"key":"ref10","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2914870"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5255-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459342"},{"key":"ref14","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"ilse","year":"2018","journal-title":"Int Conf Mach Learn"},{"key":"ref15","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.06.009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206771"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2948286"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TPAMI.2013.111","article-title":"Anomaly detection and localization in crowded scenes","volume":"36","author":"li","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2010.11.003"},{"key":"ref4","first-page":"346","article-title":"Anomaly detection using graph neural networks","author":"chaudhary","year":"0","journal-title":"Proc Int Conf Mach Learn Big Data Cloud Parallel Comput"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","first-page":"3161","article-title":"Abnormal detection using interaction energy potentials","author":"cui","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"2219","article-title":"Attention-based dropout layer for weakly supervised object localization","author":"choe","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037538"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/ICPR.2002.1044748","article-title":"Person-on-Person violence detection in video data","volume":"1","author":"datta","year":"0","journal-title":"Object recognition supported by user interaction for service robots ICPR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587510"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.006"},{"key":"ref1","first-page":"2415","article-title":"Video parsing for abnormality detection","author":"anti?","year":"0","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00560"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995524"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2234722"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref43","article-title":"Motion-aware feature for improved video anomly detection","author":"zhu","year":"2019","journal-title":"Brit Mach Vis Conf"},{"key":"ref25","first-page":"563","article-title":"W-talc: Weakly-supervised temporal activity localization and classification","author":"paul","year":"0","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09540293.pdf?arnumber=9540293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T21:31:00Z","timestamp":1661808660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9540293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3112814","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}