{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:20:59Z","timestamp":1792786859152,"version":"4.5.0"},"reference-count":81,"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 Natural Science Foundation of China","award":["62502268"],"award-info":[{"award-number":["62502268"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"China Postdoctoral Science Foundation","award":["2024M761681"],"award-info":[{"award-number":["2024M761681"]}],"id":[{"id":"https:\/\/ror.org\/0426zh255","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Beijing National Research Center for Information Science and Technology","award":["BNR2023TD03006"],"award-info":[{"award-number":["BNR2023TD03006"]}],"id":[{"id":"https:\/\/ror.org\/02tcm9e24","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3684369","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:47:12Z","timestamp":1777060032000},"page":"8839-8849","source":"Crossref","is-referenced-by-count":2,"title":["AV-Unified: A Unified Framework for Audio-Visual Scene Understanding"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-8555","authenticated-orcid":false,"given":"Guangyao","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2005.08.058"},{"key":"ref2","article-title":"Learning in audio-visual context: A review, analysis, and new perspective","author":"Wei","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref9","first-page":"386","article-title":"Audiovisual segmentation","volume-title":"Proc. 17th Euro. Conf., Comput. Vis.","author":"Zhou","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00551"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref15","first-page":"25006","article-title":"A unified audio-visual learning framework for localization, separation, and recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mo","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3593932"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01752"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02067"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00798"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2445"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0007"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3542995"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3599048"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1606"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01265"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613859"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612266"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612504"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548061"},{"key":"ref32","first-page":"16888","article-title":"Efficient test-time model adaptation without forgetting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Niu","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328298"},{"key":"ref34","first-page":"34722","article-title":"Multi-modal grouping network for weakly-supervised audio-visual video parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mo","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3672079"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680803"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32538"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3086914"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3123127"},{"key":"ref41","first-page":"737","article-title":"NAT: Neural architecture transformer for accurate and compact architectures","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Guo","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890393"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2272"},{"key":"ref45","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lu","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref52","first-page":"11449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548309"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547869"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2516"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_18"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747867"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_13"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref68","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Adv. Neural Inf. Proc. Syst.","volume":"29","author":"Lu","year":"2016"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"issue":"11","key":"ref74","first-page":"12995","article-title":"COCA: Collaborative causal regularization for audio-visual question answering","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"37","author":"Lao","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612293"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02289-z"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"ref78","article-title":"Transformer transforms salient object detection and camouflaged object detection","author":"Mao","year":"2021"},{"key":"ref79","first-page":"15448","article-title":"Learning generative vision transformer with energy-based latent space for saliency prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang","year":"2021"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405622"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29104"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11494302.pdf?arnumber=11494302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T19:13:39Z","timestamp":1791314019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11494302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3684369","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}