{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T09:46:42Z","timestamp":1784454402902,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Open Research Projects of Zhejiang Lab","award":["2021KH0AB04"],"award-info":[{"award-number":["2021KH0AB04"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202336"],"award-info":[{"award-number":["62202336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024-4-YB-03"],"award-info":[{"award-number":["2024-4-YB-03"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/taffc.2025.3559866","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T13:15:41Z","timestamp":1744290941000},"page":"2321-2333","source":"Crossref","is-referenced-by-count":12,"title":["CorMulT: A Semi-Supervised Modality Correlation-Aware Multimodal Transformer for Sentiment Analysis"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0706-4106","authenticated-orcid":false,"given":"Yangmin","family":"Li","sequence":"first","affiliation":[{"name":"Information Networking Institute, Carnegie Mellon University (CMU), Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1966-3589","authenticated-orcid":false,"given":"Ruiqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8768-6740","authenticated-orcid":false,"given":"Wengen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2010.63"},{"issue":"1","key":"ref2","first-page":"1","article-title":"Twitter mood predicts the stock market","volume-title":"J. Comput. Sci.","volume":"2","author":"Bollen","year":"2011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0894439310386557"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746418"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00305"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612051"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3155290"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945514"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276075"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s23052679"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110467"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12132986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.438"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/app13137489"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3265653"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554811"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282410"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1117\/12.2680996"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475692"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2017.23"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3139856"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.209"},{"key":"ref31","first-page":"52","article-title":"Mel-S3R: Combining mel-spectrogram and self-supervised speech representation with VQ-VAE for any-to-any voice conversion","volume-title":"Speech Commun.","volume":"151","author":"Yang","year":"2023"},{"key":"ref32","first-page":"11","article-title":"Recognizing emotions in video using multimodal DNN feature fusion","volume-title":"Proc. Grand Challenge Workshop Hum. Multimodal Lang.","author":"Williams"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1115"},{"key":"ref35","first-page":"1","article-title":"Multimodal foundation models: From specialists to general-purpose assistants","volume-title":"Found. Trends Comput. Graph. Vis.","volume":"16","author":"Li","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref37","first-page":"8992","article-title":"Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Sun"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376564"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688078"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CCAI61966.2024.10603022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446351"},{"key":"ref43","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. 2013 Conf. Empirical Methods Natural Lang. Process.","author":"Socher"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12024","article-title":"Multi-attention recurrent network for human communication comprehension","author":"Zadeh","year":"2018"},{"key":"ref45","first-page":"3718","article-title":"CH-SIMS: A Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Yu"},{"key":"ref46","first-page":"10 790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Yu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3361374"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11152495\/10960754.pdf?arnumber=10960754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:46:31Z","timestamp":1757353591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10960754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":48,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3559866","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}