{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:12:28Z","timestamp":1777497148147,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746422","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"1980-1984","source":"Crossref","is-referenced-by-count":27,"title":["Look, Listen and Pay More Attention: Fusing Multi-Modal Information for Video Violence Detection"],"prefix":"10.1109","author":[{"given":"Dong-Lai","family":"Wei","sequence":"first","affiliation":[{"name":"Fudan University,Academy for Engineering & Technology,Shanghai,China"}]},{"given":"Chen-Geng","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Melbourne,School of Computing and Information Systems,Melbourne,Australia"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering & Technology,Shanghai,China"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering & Technology,Shanghai,China"}]},{"given":"Xiao-Guang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,SEIEE,Shanghai,China"}]},{"given":"Xin-Hua","family":"Zeng","sequence":"additional","affiliation":[{"name":"Fudan University,Academy for Engineering & Technology,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425310"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12842-4_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10467-1_84"},{"key":"ref13","first-page":"322","article-title":"Not only look, but also listen: Learning multimodal violence detection under weak supervision","author":"wu","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref4","article-title":"Multi-instance learning: A survey","volume":"1","author":"zhou","year":"2004","journal-title":"Department of Computer Science & Technology Nanjing University Tech Rep"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"tran","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1007\/978-3-642-23678-5_39","article-title":"Violence detection in video using computer vision techniques","author":"nievas","year":"2011","journal-title":"International Conference on Computer Analysis of Images and Patterns"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102722"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref23","first-page":"582","article-title":"Support vector method for novelty detection","volume":"12","author":"sch\u00f6lkopf","year":"1999","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746422.pdf?arnumber=9746422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:26Z","timestamp":1660594106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746422","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}