{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T17:02:51Z","timestamp":1791046971387,"version":"4.1.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":"crossref","award":["62522116"],"award-info":[{"award-number":["62522116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62271312"],"award-info":[{"award-number":["62271312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62132006"],"award-info":[{"award-number":["62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62301316"],"award-info":[{"award-number":["62301316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Project of the State Key Laboratory of Media Convergence and Communication, Communication University of China, China","award":["SKLMCC2023KF004"],"award-info":[{"award-number":["SKLMCC2023KF004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3616155","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:39:41Z","timestamp":1759772381000},"page":"3336-3350","source":"Crossref","is-referenced-by-count":7,"title":["UNQA: Unified No-Reference Quality Assessment for Audio, Image, Video, and Audio-Visual Content"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5087-6559","authenticated-orcid":false,"given":"Yuqin","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6292-0529","authenticated-orcid":false,"given":"Yixuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8162-1949","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-5612","authenticated-orcid":false,"given":"Long","family":"Ye","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.70220\/d69zp0f4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref4","first-page":"482","article-title":"STOI-Net: A deep learning based non-intrusive speech intelligibility assessment model","volume-title":"Proc. Asia\u2013Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","author":"Zezario"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502106"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290528"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3188991"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485684"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2735192"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB55706.2022.9828590"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547872"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3470970"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2966081"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3544659"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249741"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3114509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506408"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5656-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_19"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2053549"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2894958"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00485"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.118"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277808"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01408-w"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref38","article-title":"PolyViT: Co-training vision transformers on images, videos and audio","author":"Likhosherstov","year":"2021","journal-title":"arXiv:2111.12993"},{"key":"ref39","article-title":"OmniMAE: Single model masked pretraining on images and videos","author":"Girdhar","year":"2022","journal-title":"arXiv:2206.08356"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2708503"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2955024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10182000"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref49","volume-title":"ITU-T Coded-Speech Database"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659980"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2015.7148100"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/qomex.2017.7965673"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869673"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222476"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref61","article-title":"AGAV-rater: Adapting large multimodal model for AI-generated audio-visual quality assessment","author":"Cao","year":"2025","journal-title":"arXiv:2501.18314"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"ref67","article-title":"Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound","author":"Tjandra","year":"2025","journal-title":"arXiv:2502.05139"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00267"},{"key":"ref69","first-page":"105702","article-title":"SCOREQ: Speech quality assessment with contrastive regression","author":"Ragano","year":"Dec. 2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref71","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2378061"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2562513"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2707479"},{"key":"ref77","first-page":"2125","article-title":"A no-reference audio-visual video quality metric","volume-title":"Proc. Eur. Signal Process. Conf.","author":"Martinez"},{"key":"ref78","article-title":"Audiovisual SlowFast networks for video recognition","author":"Xiao","year":"2020","journal-title":"arXiv:2001.08740"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11185171.pdf?arnumber=11185171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:10Z","timestamp":1773086470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":78,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3616155","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}