{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:27:59Z","timestamp":1778081279736,"version":"3.51.4"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0113503"],"award-info":[{"award-number":["2021ZD0113503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}],"id":[{"id":"10.13039\/501100010256","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":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3435561","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T19:51:01Z","timestamp":1722282661000},"page":"12360-12375","source":"Crossref","is-referenced-by-count":11,"title":["Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-5671","authenticated-orcid":false,"given":"Dingkang","family":"Yang","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6244-6081","authenticated-orcid":false,"given":"Mingcheng","family":"Li","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8815-7050","authenticated-orcid":false,"given":"Linhao","family":"Qu","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center, School of Basic Medical Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-2200","authenticated-orcid":false,"given":"Kun","family":"Yang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1374-7969","authenticated-orcid":false,"given":"Peng","family":"Zhai","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4152-5295","authenticated-orcid":false,"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0467-4347","authenticated-orcid":false,"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073267"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3163649"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207910"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.026"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547755"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110370"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3210836"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref15","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tsai"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.124"},{"key":"ref20","article-title":"Cross-attention is not enough: Incongruity-aware dynamic hierarchical fusion for multimodal affect recognition","author":"Wang","year":"2023","journal-title":"arXiv:2305.13583"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123718"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312858"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296196"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01871"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276075"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231437"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248271"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3324552"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28871"},{"key":"ref37","article-title":"Towards multimodal human intention understanding debiasing via subject-deconfounding","author":"Yang","year":"2024","journal-title":"arXiv:2403.05025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3645101"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3353912"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00403"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87586-2_9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_27"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3409211"},{"key":"ref44","first-page":"64","article-title":"Recurrent neural networks","volume":"5","author":"Medsker","year":"2001","journal-title":"Des. Appl."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref47","article-title":"PediatricsGPT: Large language models as Chinese medical assistants for pediatric applications","author":"Yang","year":"2024","journal-title":"arXiv:2405.19266"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01183"},{"key":"ref49","first-page":"25151","article-title":"How2comm: Communication-efficient and collaboration-pragmatic multi-agent perception","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506181"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC48188.2019.8949228"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"ref55","article-title":"Image-text multi-modal representation learning by adversarial backpropagation","author":"Park","year":"2016","journal-title":"arXiv:1612.08354"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref57","first-page":"343","article-title":"Domain separation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bousmalis"},{"key":"ref58","first-page":"3543","article-title":"Attention is not explanation","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Jain"},{"key":"ref59","volume-title":"Predictive attention transformer: Improving transformer with attention map prediction","author":"Wang","year":"2021"},{"key":"ref60","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273600"},{"key":"ref62","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ganin"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_9"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10614188.pdf?arnumber=10614188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:38:30Z","timestamp":1736368710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10614188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":71,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3435561","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}