{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:31:27Z","timestamp":1770917487513,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62207029"],"award-info":[{"award-number":["62207029"]}],"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":["62271454"],"award-info":[{"award-number":["62271454"]}],"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":["62176018"],"award-info":[{"award-number":["62176018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2018YFB1403903"],"award-info":[{"award-number":["2018YFB1403903"]}]},{"name":"National Key Research and Development Program of China","award":["2021YFF0900700"],"award-info":[{"award-number":["2021YFF0900700"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L223033"],"award-info":[{"award-number":["L223033"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tnnls.2023.3282953","type":"journal-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T13:27:54Z","timestamp":1686922074000},"page":"222-236","source":"Crossref","is-referenced-by-count":38,"title":["Weakening the Dominant Role of Text: CMOSI Dataset and Multimodal Semantic Enhancement Network"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0464-9862","authenticated-orcid":false,"given":"Cong","family":"Jin","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering and the State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}]},{"given":"Cong","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering and the State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8979-8490","authenticated-orcid":false,"given":"Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering and the State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6850-9335","authenticated-orcid":false,"given":"Guangzhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1072-8279","authenticated-orcid":false,"given":"Guixuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation (IA), Chinese Academy of Sciences (CAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6013-6351","authenticated-orcid":false,"given":"Shuwu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02145-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3038167"},{"key":"ref3","first-page":"1","article-title":"MULTIBENCH: Multiscale benchmarks for multimodal representation learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref4","article-title":"MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016","journal-title":"arXiv:1606.06259"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref7","article-title":"DravidianMultiModality: A dataset for multi-modal sentiment analysis in Tamil and Malayalam","author":"Chakravarthi","year":"2021","journal-title":"arXiv:2106.04853"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.09.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.109"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979225"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107676"},{"key":"ref16","article-title":"ScaleVLAD: Improving multimodal sentiment analysis via multi-scale fusion of locally descriptors","author":"Luo","year":"2022","journal-title":"arXiv:2112.01368"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63031-7_26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556630"},{"key":"ref19","article-title":"Robust-MSA: Understanding the impact of modality noise on multimodal sentiment analysis","author":"Mao","year":"2022","journal-title":"arXiv:2211.13484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00335"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref22","first-page":"973","article-title":"Utterance-level multimodal sentiment analysis","volume-title":"Proc. 51st Annu. Meeting Assoc. Comput. Linguistics","author":"P\u00e9rez-Rosas"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.34"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-016-0406-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref26","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12153"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12065"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2957872"},{"key":"ref30","article-title":"Factorized multimodal transformer for multimodal sequential learning","author":"Zadeh","year":"2019","journal-title":"arXiv:1911.09826"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1382"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3380688.3380693"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390698"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3093416"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68780-9_26"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3210433"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3171679"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3236320"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109050"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-demo.12"},{"key":"ref43","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.06.009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-3302"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.134"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10832116\/10154459.pdf?arnumber=10154459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:12Z","timestamp":1764959952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10154459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":55,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3282953","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}