{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:29:21Z","timestamp":1783542561087,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Centre for Advances in Reliability and Safety (CAiRs) through the Utilization of the CAiRs Secondment Fund","award":["68BS"],"award-info":[{"award-number":["68BS"]}]},{"name":"Research Platform for Advanced Audio and Speech Signal Processing"},{"name":"Innovation Technology Company Ltd.","award":["P0049192"],"award-info":[{"award-number":["P0049192"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3674552","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:17:19Z","timestamp":1773692239000},"page":"10260-10275","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Branch Aesthetic and Technical Perspectives With Cross Tri-Fusion Attention for No-Reference Audio-Visual Quality Assessment"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8180-7994","authenticated-orcid":false,"given":"Ngai-Wing","family":"Kwong","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1473-094X","authenticated-orcid":false,"given":"Yui-Lam","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3162-6105","authenticated-orcid":false,"given":"Ziyin","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8578-0696","authenticated-orcid":false,"given":"Sik-Ho","family":"Tsang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Chu Hai College, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3347172"},{"key":"ref3","volume-title":"Global 2022 Forecast Highlights","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2478706"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2257632"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3470970"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350990"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2881828"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3005111"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181496"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3466925"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.4921674"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2017.8299900"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/conatel.2011.5958657"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3477291"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24425\/ijet.2024.149549"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3122347"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2214933"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01323"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3209007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207148"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249741"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX55416.2022.9900891"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_46"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123142"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1117\/12.2042425"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290528"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506408"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251695"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3616155"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3522855"},{"key":"ref43","article-title":"Disentangling aesthetic and technical effects for video quality assessment of user generated content","author":"Wu","year":"2022","journal-title":"arXiv:2211.04894"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611737"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00640"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.1998-350"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref48","first-page":"745","article-title":"Objective quality assessment based on low bit rate audio","volume-title":"Proc. 8th Int. Conf. Comput. Technol. Inf. Manage. (NCM ICNIT)","volume":"2","author":"Jiang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558180"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3139010"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413845"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"ref55","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Aytar"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref60","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski"},{"key":"ref61","volume-title":"Final Report From the Video Quality Experts Group on the Validation of Objective Quality Metrics for Video Quality Assessment","year":"2000"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref64","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref65","article-title":"YOLOv11: An overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv:2410.17725"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11435472.pdf?arnumber=11435472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:46:03Z","timestamp":1783539963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11435472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":65,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3674552","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}