{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:52:14Z","timestamp":1791489134467,"version":"4.3.4"},"reference-count":124,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Anhui Provincial Natural Science Foundation","award":["2408085J040"],"award-info":[{"award-number":["2408085J040"]}]},{"name":"National Key R&D Program of China","award":["2024YFB3311602"],"award-info":[{"award-number":["2024YFB3311602"]}]},{"name":"Natural Science Foundation of China","award":["62272144"],"award-info":[{"award-number":["62272144"]}]},{"name":"Major Project of Anhui Provincial Science and Technology Breakthrough Program","award":["202423k09020001"],"award-info":[{"award-number":["202423k09020001"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["JZ2024HGTG0309"],"award-info":[{"award-number":["JZ2024HGTG0309"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3723653","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T19:09:34Z","timestamp":1786648174000},"page":"15347-15364","source":"Crossref","is-referenced-by-count":0,"title":["Robust Audio-Visual Question Answering With Missing Modality in Training and Testing"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6402-7593","authenticated-orcid":false,"given":"Jinxing","family":"Zhou","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, UAE"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2227-8826","authenticated-orcid":false,"given":"Zhangbin","family":"Li","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7118-6733","authenticated-orcid":false,"given":"Di","family":"Hu","sequence":"additional","affiliation":[{"name":"Renmin University of China","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9401-4432","authenticated-orcid":false,"given":"Yanghao","family":"Zhou","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9041-2214","authenticated-orcid":false,"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, UAE"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8230-9065","authenticated-orcid":false,"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, UAE"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-254X","authenticated-orcid":false,"given":"Dan","family":"Guo","sequence":"additional","affiliation":[{"name":"Hefei University of Technology and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446292"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_3"},{"key":"ref3","article-title":"Learning in audio-visual context: A review, analysis, and new perspective","author":"Wei","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref9","article-title":"Improving audio-visual video parsing with pseudo visual labels","author":"Zhou","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02142-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33185"},{"key":"ref12","article-title":"Face-guided sentiment boundary enhancement for weakly-supervised temporal sentiment localization","author":"Han","year":"2026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00783"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i16.38374"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32704"},{"key":"ref16","article-title":"See the emotion: A facial emoji proxy modeling for EEG emotion recognition","author":"Hu","year":"2026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i3.37175"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3721981"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2026.3714823"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02525"},{"key":"ref22","article-title":"Audit after segmentation: Reference-free mask quality assessment for language-referred audio-visual segmentation","author":"Zhou","year":"2026"},{"key":"ref23","first-page":"9","article-title":"Audio-visual interpretable and controllable video captioning","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Tian","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3175012"},{"key":"ref27","article-title":"Autoregressive image generation with linear complexity: A spatial-aware decay perspective","author":"Mao","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680612"},{"key":"ref29","article-title":"A benchmark and agentic framework for omni-modal reasoning and tool use in long videos","author":"Kurpath","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.acl-long.913"},{"key":"ref31","article-title":"MTAVG-Bench 2.0: Diagnosing failure modes of cinematic expressiveness in multi-talker audio-video generation","author":"Li","year":"2026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00094"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33709"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127885"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3735975"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681586"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i16.38373"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP55912.2026.11461803"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01265"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01277"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318220"},{"key":"ref45","article-title":"Answering diverse questions via text attached with key audio-visual clues","author":"Ye","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28116"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680803"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612293"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32538"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2445"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.159"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3642821"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32538"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612132"},{"key":"ref56","first-page":"1","article-title":"AV-Mamba: Cross-modality selective state space models for audio-visual question answering","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Huang","year":"2024"},{"key":"ref57","first-page":"1","article-title":"Mamba: Linear-Time sequence modeling with selective state spaces","author":"Gu","year":"2024","journal-title":"COLM"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3597461"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3479776"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref61","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1570"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1606"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2943456"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0812"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.intell.2008.08.004"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)00138-0"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02499"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0302"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2947232"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3280222"},{"key":"ref76","article-title":"Audio inpainting with generative adversarial network","author":"Ebner","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00674"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00768"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3587578"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3476487"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29189"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33731"},{"key":"ref83","first-page":"1","article-title":"Deep incomplete multi-view learning via cyclic permutation of VAEs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gao","year":"2025"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01102"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155499"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/435"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974828"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3238416"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3112114"},{"key":"ref90","article-title":"What makes for robust multi-modal models in the face of missing modalities?","author":"Li","year":"2023"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02272"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02323"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02591"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33984"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01277"},{"key":"ref97","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref98","article-title":"Billion-scale semi-supervised learning for image classification","author":"Yalniz","year":"2019"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref101","first-page":"1","article-title":"In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning","author":"Rizve","year":"2021"},{"key":"ref102","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zoph","year":"2020"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01485"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02004"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110166"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01895"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/467"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00612"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3221"},{"key":"ref113","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":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447949"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681683"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02147"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00628"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.03.003"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11654509.pdf?arnumber=11654509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:12:00Z","timestamp":1791486720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11654509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":124,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3723653","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11]]}}}