{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:10:13Z","timestamp":1775027413255,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62276237"],"award-info":[{"award-number":["62276237"]}],"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":["62036009"],"award-info":[{"award-number":["62036009"]}],"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":["62432014"],"award-info":[{"award-number":["62432014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017577","name":"Basic Public Welfare Research Program of Zhejiang Province","doi-asserted-by":"publisher","award":["LTGY23F020006"],"award-info":[{"award-number":["LTGY23F020006"]}],"id":[{"id":"10.13039\/501100017577","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F0202"],"award-info":[{"award-number":["LDT23F0202"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F02021F02"],"award-info":[{"award-number":["LDT23F02021F02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3458812","type":"journal-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T20:04:03Z","timestamp":1726085043000},"page":"4105-4120","source":"Crossref","is-referenced-by-count":5,"title":["TriSAT: Trimodal Representation Learning for Multimodal Sentiment Analysis"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2555-343X","authenticated-orcid":false,"given":"Ruohong","family":"Huan","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1391-0957","authenticated-orcid":false,"given":"Guowei","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6122-0574","authenticated-orcid":false,"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2077-9608","authenticated-orcid":false,"given":"Ronghua","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/72.286928"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3068598"},{"key":"ref7","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.412"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_21"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref17","first-page":"12113","article-title":"Deep multimodal multilinear fusion with high-order polynomial pooling","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"32","author":"Hou","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1208"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"ref22","first-page":"1","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tsai","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1046"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1566"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s23052679"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/480"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref38","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref39","first-page":"1849","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Sohn","year":"2016"},{"key":"ref40","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Khosla","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"ref42","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref45","first-page":"1","article-title":"Adam: A. method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref47","first-page":"960","volume-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process.","author":"Degottex","year":"2014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1121\/1.2935783"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"11","key":"ref50","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10675444.pdf?arnumber=10675444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:29:55Z","timestamp":1727112595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10675444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3458812","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}