{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T18:34:04Z","timestamp":1782585244275,"version":"3.54.5"},"reference-count":53,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62111530145"],"award-info":[{"award-number":["62111530145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771200"],"award-info":[{"award-number":["61771200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61571192"],"award-info":[{"award-number":["61571192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61301300"],"award-info":[{"award-number":["61301300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515011687"],"award-info":[{"award-number":["2022A1515011687"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021A1515011454"],"award-info":[{"award-number":["2021A1515011454"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of the International Science and Technology Collaboration of Guangdong Province","award":["2021A0505030003"],"award-info":[{"award-number":["2021A0505030003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3184533","type":"journal-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T20:22:25Z","timestamp":1655756545000},"page":"4922-4932","source":"Crossref","is-referenced-by-count":19,"title":["Audiovisual Dependency Attention for Violence Detection in Videos"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9443-7208","authenticated-orcid":false,"given":"Wenfeng","family":"Pang","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9079-4566","authenticated-orcid":false,"given":"Qianhua","family":"He","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4362-1125","authenticated-orcid":false,"given":"Yanxiong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4954-8398","authenticated-orcid":false,"given":"Jichen","family":"Yang","sequence":"additional","affiliation":[{"name":"Speech Information Security Laboratory, School of Cyberspace Security, Guangdong Polytechnic Normal University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.009"},{"key":"ref12","article-title":"Multi-instance learning: A survey","volume":"1","author":"zhou","year":"2004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12319"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref52","first-page":"24","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"0","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11012-3_24"},{"key":"ref17","first-page":"768","article-title":"Lip movement and speech synchronization detection based on multimodal shift-invariant dictionary","author":"zhu","year":"0","journal-title":"Proc IEEE Conf Intell Comput Intell Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557721"},{"key":"ref18","first-page":"973","article-title":"Liveness detection using time drift between lip movement and voice","author":"zhu","year":"0","journal-title":"Proc Int Conf Mach Learn Cybern"},{"key":"ref51","first-page":"582","article-title":"Support vector method for novelty detection","volume":"12","author":"sch\u00f6lkopf","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"ref46","first-page":"6299","article-title":"Quo vadis, action recognition? A new model and the kinetics datase","author":"carreira","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683676"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref44","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3320061"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-3002-4_43"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078468"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854259"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2002.1044748"},{"key":"ref40","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00406"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-1984-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.06.009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICMCS.2014.6911186"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2986969"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.03.005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1007\/s11263-018-1083-5","article-title":"Learning sight from sound: Ambient sound provides supervision for visual learning","volume":"126","author":"andrew","year":"2018","journal-title":"Int J Comput Vis"},{"key":"ref20","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume":"29","author":"aytar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10467-1_84"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12842-4_13"},{"key":"ref29","first-page":"200","article-title":"Cassandra: Audio-video sensor fusion for aggression detection","author":"wojtek","year":"0","journal-title":"Proc IEEE Con Advanced Video Signal Based Surveill"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09801710.pdf?arnumber=9801710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:04:41Z","timestamp":1701115481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9801710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3184533","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}