{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:40:38Z","timestamp":1778348438781,"version":"3.51.4"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["62276180"],"award-info":[{"award-number":["62276180"]}],"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":["61976149"],"award-info":[{"award-number":["61976149"]}],"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":["62406217"],"award-info":[{"award-number":["62406217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LZ20F020002"],"award-info":[{"award-number":["LZ20F020002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LQ24F020014"],"award-info":[{"award-number":["LQ24F020014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Zhejiang","award":["2024C01022"],"award-info":[{"award-number":["2024C01022"]}]},{"name":"Humanities and Social Science Project of the Chinese Ministry of Education","award":["24YJCZH285"],"award-info":[{"award-number":["24YJCZH285"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tcsvt.2025.3571534","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T13:17:05Z","timestamp":1747747025000},"page":"9809-9822","source":"Crossref","is-referenced-by-count":29,"title":["MDKAT: Multimodal Decoupling With Knowledge Aggregation and Transfer for Video Emotion Recognition"],"prefix":"10.1109","volume":"35","author":[{"given":"Jian","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}]},{"given":"Chenglong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}]},{"given":"Lin","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}]},{"given":"Shuchang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5490-3921","authenticated-orcid":false,"given":"Dandan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8184-5088","authenticated-orcid":false,"given":"Shiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4708-4171","authenticated-orcid":false,"given":"Xiaoming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2731-5403","authenticated-orcid":false,"given":"Siwei","family":"Ma","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Cloud and AI, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121692"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-44673-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3312263"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236320"},{"key":"ref8","first-page":"7020","article-title":"Mucdn: Mutual conversational detachment network for emotion recognition in multi-party conversations","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Zhao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13360-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref11","first-page":"7124","article-title":"Modeling intra-and inter-modal relations: Hierarchical graph contrastive learning for multimodal sentiment analysis","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Lin"},{"key":"ref12","first-page":"7136","article-title":"Amoa: Global acoustic feature enhanced modal-order-aware network for multimodal sentiment analysis","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376564"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102861"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746910"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29374"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29873"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247822"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312858"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273577"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688018"},{"key":"ref27","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01610"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-74"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2018.00043"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3093923"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447640"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3282953"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321404"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCECE61317.2024.10504175"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103675"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105052"},{"key":"ref43","first-page":"9120","article-title":"Integrating representation subspace mapping with unimodal auxiliary loss for attention-based multimodal emotion recognition","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics, Lang. Resour. Eval.","author":"Du"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218018"},{"key":"ref45","first-page":"1","article-title":"Domain separation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bousmalis"},{"key":"ref46","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276075"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612053"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446571"},{"key":"ref50","article-title":"MInD: Improving multimodal sentiment analysis via multimodal information disentanglement","author":"Dai","year":"2024","journal-title":"arXiv:2401.11818"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"ref54","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref57","first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","volume-title":"Proc. Conf. Empir. Methods Nat. Lang. Process.","author":"Zadeh"},{"key":"ref58","first-page":"2247","article-title":"Efficient low-rank multimodal fusion with modality-specific factors","volume-title":"Proc. 56th Annu. Meeting Assoc. Comput. Linguistics","author":"Liu"},{"key":"ref59","article-title":"Learning factorized multimodal representations","author":"Hubert Tsai","year":"2018","journal-title":"arXiv:1806.06176"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11192799\/11007210.pdf?arnumber=11007210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:40:35Z","timestamp":1759772435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":62,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3571534","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}