{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T15:33:04Z","timestamp":1788017584826,"version":"build-2784847793"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Project of Science and Technology Innovation 2030","award":["2018AAA0101302"],"award-info":[{"award-number":["2018AAA0101302"]}]},{"name":"General Program of National Natural Science Foundation of China NSFC","award":["61773300"],"award-info":[{"award-number":["61773300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3147369","type":"journal-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:35:25Z","timestamp":1643747725000},"page":"1674-1685","source":"Crossref","is-referenced-by-count":98,"title":["Weakly Supervised Audio-Visual Violence Detection"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2938-6798","authenticated-orcid":false,"given":"Peng","family":"Wu","sequence":"first","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4544-760X","authenticated-orcid":false,"given":"Xiaotao","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6834-5350","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12842-4_13"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10467-1_84"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_25"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref58","article-title":"Equivalent classification mapping for weakly supervised temporal action localization","author":"zhao","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288397"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412502"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_42"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107515"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425310"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00829"},{"key":"ref10","first-page":"8276","article-title":"Toward aubjective violence detection in videos","author":"peixoto","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref17","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933554"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref18","article-title":"See, hear, and read: Deep aligned representations","author":"aytar","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref50","first-page":"270","article-title":"Motion-aware feature for improved video anomaly detection","author":"zhu","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref45","first-page":"582","article-title":"Support vector method for novelty detection","author":"sch\u00f6lkopf","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2019.8909882"},{"key":"ref8","first-page":"280","article-title":"Bidirectional convolutional LSTM for the detection of violence in videos","author":"hanson","year":"2018","journal-title":"Proc Eur Conf Comput Vis Workshop"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00214"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683676"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-1984-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3112784"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3090769"},{"key":"ref35","article-title":"Cross-attentional audio-visual fusion for weakly-supervised action localization","author":"lee","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2237023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00560"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.793"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2007.4412825"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00877"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007511"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3013166"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093620"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"ref1","first-page":"332","article-title":"Violence detection in video using computer vision techniques","author":"bermejo","year":"2010","journal-title":"Proc Int Conf Comput Anal Images Patterns"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"ref38","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":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00277"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01473-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073235"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413686"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref60","article-title":"When, where, and what? A new dataset for anomaly detection in driving videos","author":"yao","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2959425"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09699377.pdf?arnumber=9699377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:45:09Z","timestamp":1687805109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9699377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3147369","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}