{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:50:25Z","timestamp":1793206225684,"version":"4.5.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021YFF0900900"],"award-info":[{"award-number":["2021YFF0900900"]}]},{"name":"NSFC","award":["U21A20471"],"award-info":[{"award-number":["U21A20471"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Guangdong NSF Project","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]},{"name":"Guangdong Provincial Key Laboratory of Information Security Technology","award":["2023B1212060026"],"award-info":[{"award-number":["2023B1212060026"]}],"id":[{"id":"https:\/\/ror.org\/03xyaz886","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Guangzhou Basic and Applied Basic Research Scheme","award":["2024A04J4067"],"award-info":[{"award-number":["2024A04J4067"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3535377","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T13:54:42Z","timestamp":1737986082000},"page":"2047-2058","source":"Crossref","is-referenced-by-count":17,"title":["Audio-Visual Collaborative Learning for Weakly Supervised Video Anomaly Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5437-3070","authenticated-orcid":false,"given":"Jingke","family":"Meng","sequence":"first","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huilin","family":"Tian","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4799-8525","authenticated-orcid":false,"given":"Ge","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2678-5373","authenticated-orcid":false,"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3161061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147369"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413686"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803657"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3112814"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292596"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037538"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3175611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00726"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5255-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102722"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150469"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156758"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00089"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125995"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475583"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475298"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00213"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"ref28","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Nagrani","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144885"},{"key":"ref31","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref34","first-page":"11846","article-title":"QVHighlights: Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lei","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270624"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref38","first-page":"11449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lin","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01011"},{"key":"ref40","first-page":"9774","article-title":"TriBERT: Human-centric audio-visual representation learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Rahman","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00034"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00223"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref45","first-page":"1","article-title":"Learning to set waypoints for audio-visual navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2020"},{"key":"ref46","first-page":"29258","article-title":"How does it sound?","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Su","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"ref49","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ngiam","year":"2011"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00684"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3522384"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683676"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00269"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547868"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01561"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/10855604.pdf?arnumber=10855604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:44:43Z","timestamp":1790743483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10855604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535377","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}