{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:59:45Z","timestamp":1780765185023,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":"publisher","award":["62202311"],"award-info":[{"award-number":["62202311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376099"],"award-info":[{"award-number":["62376099"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Excellent Science and Technology Creative Talent Training Program of Shenzhen Municipality","award":["RCBS20221008093224017"],"award-info":[{"award-number":["RCBS20221008093224017"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011512"],"award-info":[{"award-number":["2023A1515011512"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Scientific Research Project of the Department of Education of Guangdong Province","award":["2024ZDZX3012"],"award-info":[{"award-number":["2024ZDZX3012"]}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515010989"],"award-info":[{"award-number":["2024A1515010989"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3579549","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T13:53:28Z","timestamp":1749822808000},"page":"12292-12305","source":"Crossref","is-referenced-by-count":2,"title":["Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8694-4245","authenticated-orcid":false,"given":"Runhao","family":"Zeng","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaicheng","family":"Niu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4769-1526","authenticated-orcid":false,"given":"Jian","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-699X","authenticated-orcid":false,"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3529-2640","authenticated-orcid":false,"given":"Victor C. M.","family":"Leung","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_36"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01367"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"ref5","first-page":"1","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref6","first-page":"38629","article-title":"MEMO: Test time robustness via adaptation and augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref7","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Iwasawa"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01435"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00816"},{"key":"ref10","first-page":"29374","article-title":"Test-time training with masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Gandelsman"},{"key":"ref11","first-page":"16888","article-title":"Efficient test-time model adaptation without forgetting","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Niu"},{"key":"ref12","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref13","first-page":"21808","article-title":"TTT++: When does self-supervised test-time training fail or thrive?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Liu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02198"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612153"},{"key":"ref16","first-page":"1","article-title":"Temporal coherent test time optimization for robust video classification","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yi"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3535385"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32509"},{"key":"ref23","first-page":"17543","article-title":"Revisiting realistic test-time training: Sequential inference and adaptation by anchored clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Su"},{"key":"ref24","article-title":"Evaluating prediction-time batch normalization for robustness under covariate shift","author":"Nado","year":"2020","journal-title":"arXiv:2006.10963"},{"key":"ref25","article-title":"SITA: Single image test-time adaptation","author":"Khurana","year":"2021","journal-title":"arXiv:2112.02355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285046"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3410041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3412243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref30","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Alwassel"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727435"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","first-page":"1","article-title":"Polyvit: Co-training vision transformers on images, videos and audio","volume":"2023","author":"Likhosherstov","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref37","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Nagrani"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475321"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3486344"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337134"},{"key":"ref42","article-title":"Cross-domain first person audio-visual action recognition through relative norm alignment","author":"Planamente","year":"2021","journal-title":"arXiv:2106.01689"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"ref44","article-title":"EPIC-KITCHENS-100 unsupervised domain adaptation challenge for action recognition 2021: Team M3EM technical report","volume-title":"arXiv:2106.10026","author":"Yang","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"ref46","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref47","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Schneider"},{"key":"ref48","first-page":"1","article-title":"Entropy is not enough for test-time adaptation: From the perspective of disentangled factors","volume-title":"Proc. 12th Int. Conf. Learn. Represent. (ICLR)","author":"Lee"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00254"},{"key":"ref50","article-title":"Audiovisual moments in time: A large-scale annotated dataset of audiovisual actions","author":"Joannou","year":"2023","journal-title":"arXiv:2308.09685"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref54","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01412"},{"key":"ref56","first-page":"1","article-title":"Benchmarking the robustness of spatial\u2013temporal models against corruptions","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Yi"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","article-title":"Gpt-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref61","volume-title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","year":"2024"},{"key":"ref62","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref63","volume-title":"Binggpt: Desktop Application of New Bing\u2019s Ai-Powered Chat","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3483009"},{"key":"ref65","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn., (ICML)","author":"Chen"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01719"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11036107.pdf?arnumber=11036107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:43:07Z","timestamp":1765219387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11036107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":66,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3579549","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}