{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:36:20Z","timestamp":1780356980372,"version":"3.54.1"},"reference-count":134,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100018543","name":"Natural Science Foundation of Xinjiang Uygur Autonomous Region","doi-asserted-by":"publisher","award":["2022D01C429"],"award-info":[{"award-number":["2022D01C429"]}],"id":[{"id":"10.13039\/501100018543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018543","name":"Natural Science Foundation of Xinjiang Uygur Autonomous Region","doi-asserted-by":"publisher","award":["2022D01C427"],"award-info":[{"award-number":["2022D01C427"]}],"id":[{"id":"10.13039\/501100018543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017366","name":"Key Research and Development Program of Xinjiang Uygur Autonomous Region","doi-asserted-by":"publisher","award":["2022B01046"],"award-info":[{"award-number":["2022B01046"]}],"id":[{"id":"10.13039\/100017366","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3554665","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:47:44Z","timestamp":1742975264000},"page":"64556-64583","source":"Crossref","is-referenced-by-count":15,"title":["Multimodal Sentiment Analysis\u2014A Comprehensive Survey From a Fusion Methods Perspective"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9859-8471","authenticated-orcid":false,"given":"Kai","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Ürümqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9319-1919","authenticated-orcid":false,"given":"Mingsheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Ürümqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9101-7622","authenticated-orcid":false,"given":"Qingguan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Ürümqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5035-7194","authenticated-orcid":false,"given":"Jianing","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.102447"},{"key":"ref2","article-title":"Will affective computing emerge from foundation models and general AI? A first evaluation on ChatGPT","author":"Amin","year":"2023","journal-title":"arXiv:2303.03186"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3419593"},{"key":"ref4","first-page":"7814","article-title":"Good or bad news? Exploring GPT-4 for sentiment analysis for faroese on a public news corpora","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics, Language Resour. Eval.","author":"Debess"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.135"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3222023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3689062.3689088"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3606039.3613114"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612181"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.821"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651971"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3155604"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178204"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110502"},{"key":"ref19","article-title":"Neuro-inspired information-theoretic hierarchical perception for multimodal learning","author":"Xiao","year":"2024","journal-title":"arXiv:2404.09403"},{"key":"ref20","first-page":"9073","article-title":"Infoenh: Towards multimodal sentiment analysis via information bottleneck filter and optimal transport alignment","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics, Language Resour. Eval.","author":"Xie"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.189"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.219"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197420"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6243347"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3652149"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554809"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111346"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3430543"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.01.019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3586075"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3276075"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01345-5"},{"key":"ref37","article-title":"Curriculum learning meets weakly supervised modality correlation learning","author":"Mai","year":"2022","journal-title":"arXiv:2212.07619"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3267882"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.980"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101973"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548211"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746418"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102085"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08366-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3363028"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233070"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3423671"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532064"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547906"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.2"},{"issue":"1","key":"ref55","first-page":"1","article-title":"M3GAT: A multi-modal, multi-task interactive graph attention network for conversational sentiment analysis and emotion recognition","volume":"42","author":"Zhang","year":"2024","journal-title":"ACM Trans. Inf. Syst."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612051"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.860"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096644"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/2105593"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9860014"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3265653"},{"key":"ref62","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":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119240"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126992"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747542"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_18"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.649"},{"key":"ref68","first-page":"6795","article-title":"Towards exploiting sticker for multimodal sentiment analysis in social media: A new dataset and baseline","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Ge"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109259"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107676"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746536"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-05151-w"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref74","first-page":"1118","article-title":"Cross-language text classification using structural correspondence learning","volume-title":"Proc. 48th Annu. Meeting Assoc. Comput. Linguistics","author":"Prettenhofer"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref76","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":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s16-1002"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref79","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2018","journal-title":"arXiv:1810.02508"},{"key":"ref80","article-title":"Towards multimodal sarcasm detection (An_Obviously_perfect paper)","author":"Castro","year":"2019","journal-title":"arXiv:1906.01815"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.188"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.141"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114794"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3559866"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"ref89","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019","journal-title":"arXiv:1910.13461"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612336"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.519"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349350"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2024.200410"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.109"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171679"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.27078"},{"key":"ref100","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski"},{"issue":"4","key":"ref101","first-page":"534","article-title":"Multi-task learning 3D CNN-BLSTM with attention mechanism for speech emotion recognition","volume":"48","author":"Te","year":"2022","journal-title":"J. East China Univ. Sci. Technol."},{"issue":"1","key":"ref102","first-page":"109","article-title":"Eeg emotion recognition based on hybrid neural networks","volume":"53","author":"Dongli","year":"2021","journal-title":"J. South China normal Univ."},{"key":"ref103","first-page":"59","article-title":"OpenFace 2.0: Facial behavior analysis toolkit","volume-title":"Proc. 13th IEEE Int. Conf. Autom. Face Gesture Recognit. (FG)","author":"Baltrusaitis"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3324552"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.031"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2090"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00628"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376564"},{"key":"ref109","article-title":"Multimodal representations learning based on mutual information maximization and minimization and identity embedding for multimodal sentiment analysis","author":"Zheng","year":"2022","journal-title":"arXiv:2201.03969"},{"key":"ref110","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":"ref111","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195179644.001.0001"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3224929"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119125"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.50"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103229"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3649447"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3071503"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26438-2_25"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531900"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548137"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11234-y"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/3572915"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3303711"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338769"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_27"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3250499"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101958"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103538"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102031"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-022-10073-9"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282410"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207572"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10938581.pdf?arnumber=10938581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T17:40:37Z","timestamp":1745257237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":134,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3554665","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}