{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:25:13Z","timestamp":1774016713917,"version":"3.50.1"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62422204"],"award-info":[{"award-number":["62422204"]}],"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":["62472133"],"award-info":[{"award-number":["62472133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Province Natural Science Foundation","doi-asserted-by":"publisher","award":["LMS26F020018"],"award-info":[{"award-number":["LMS26F020018"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.patcog.2026.113315","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T19:55:39Z","timestamp":1771358139000},"page":"113315","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Emotional conflict adaptation for multimodal sentiment analysis"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2131-9200","authenticated-orcid":false,"given":"Tingting","family":"Han","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6367-650X","authenticated-orcid":false,"given":"Lingyun","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1842-4050","authenticated-orcid":false,"given":"Min","family":"Tan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-1137","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3298-2574","authenticated-orcid":false,"given":"Hongxun","family":"Yao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.patcog.2026.113315_bib0001","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MIS.2016.94","article-title":"Multimodal sentiment intensity analysis in videos: facial gestures and verbal messages","volume":"31","author":"Zadeh","year":"2016","journal-title":"IEEE Intell. Syst."},{"issue":"10","key":"10.1016\/j.patcog.2026.113315_bib0002","doi-asserted-by":"crossref","first-page":"6729","DOI":"10.1109\/TPAMI.2021.3094362","article-title":"Affective image content analysis: two decades review and new perspectives","volume":"44","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113315_bib0003","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"1122","article-title":"Misa: modality-invariant and-specific representations for multimodal sentiment analysis","author":"Hazarika","year":"2020"},{"key":"10.1016\/j.patcog.2026.113315_bib0004","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"1642","article-title":"Disentangled representation learning for multimodal emotion recognition","author":"Yang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113315_bib0005","series-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","first-page":"7617","article-title":"Confede: contrastive feature decomposition for multimodal sentiment analysis","author":"Yang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113315_bib0006","doi-asserted-by":"crossref","DOI":"10.1109\/MIS.2016.94","article-title":"Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.patcog.2026.113315_bib0007","series-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","first-page":"2236","article-title":"Multimodal language analysis in the wild: cmu-mosei dataset and interpretable dynamic fusion graph","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.patcog.2026.113315_bib0008","series-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","first-page":"3718","article-title":"Ch-sims: a Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality","author":"Yu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113315_bib0009","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","article-title":"Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions","volume":"91","author":"Gandhi","year":"2023","journal-title":"Inform. Fusion"},{"key":"10.1016\/j.patcog.2026.113315_bib0010","series-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","first-page":"1103-1114","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.patcog.2026.113315_bib0011","series-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","first-page":"2247-2256","article-title":"Efficient low-rank multimodal fusion with modality-specific factors","author":"Liu","year":"2018"},{"key":"10.1016\/j.patcog.2026.113315_bib0012","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7216","article-title":"Words can shift: dynamically adjusting word representations using nonverbal behaviors","volume":"33","author":"Wang","year":"2019"},{"key":"10.1016\/j.patcog.2026.113315_bib0013","series-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","first-page":"2359-2369","article-title":"Integrating multimodal information in large pretrained transformers","volume":"2020","author":"Rahman","year":"2020"},{"key":"10.1016\/j.patcog.2026.113315_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109259","article-title":"TETFN: A text enhanced transformer fusion network for multimodal sentiment analysis","volume":"136","author":"Wang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113315_bib0015","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"521","article-title":"Cm-bert: cross-modal bert for text-audio sentiment analysis","author":"Yang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113315_bib0016","series-title":"Proceedings of the IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Nhfnet: a non-homogeneous fusion network for multimodal sentiment analysis","author":"Fu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113315_bib0017","series-title":"Proceedings of the IEEE International Conference on Multimedia and Expo","first-page":"1367","article-title":"Multimodal sentiment analysis with preferential fusion and distance-aware contrastive learning","author":"Ma","year":"2023"},{"key":"10.1016\/j.patcog.2026.113315_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110847","article-title":"Sentiment analysis based on text information enhancement and multimodal feature fusion","volume":"156","author":"Liu","year":"2024","journal-title":"Pattern Recognit."},{"issue":"10","key":"10.1016\/j.patcog.2026.113315_bib0019","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1109\/JPROC.2023.3309299","article-title":"Toward label-efficient emotion and sentiment analysis","volume":"111","author":"Zhao","year":"2023","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.patcog.2026.113315_bib0020","series-title":"Proceedings of the Conference. Association for Computational Linguistics. Meeting","first-page":"6558-6569","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"2019","author":"Tsai","year":"2019"},{"key":"10.1016\/j.patcog.2026.113315_bib0021","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8148","article-title":"Attention is not enough: mitigating the distribution discrepancy in asynchronous multimodal sequence fusion","author":"Liang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113315_bib0022","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"833","article-title":"Acformer: an aligned and compact transformer for multimodal sentiment analysis","author":"Zong","year":"2023"},{"key":"10.1016\/j.patcog.2026.113315_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111785","article-title":"CIEG-Net: Context information enhanced gated network for multimodal sentiment analysis","volume":"168","author":"Chen","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113315_bib0024","article-title":"SDRS: sentiment-aware disentangled representation shifting for multimodal sentiment analysis","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113315_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130475","article-title":"Consistency and discrepancy information learning in multimodal sentiment analysis via maximizing mutual information and contrastive learning","volume":"302","author":"Wang","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113315_bib0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6631","article-title":"Decoupled multimodal distilling for emotion recognition","author":"Li","year":"2023"},{"issue":"3","key":"10.1016\/j.patcog.2026.113315_bib0027","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1109\/TAFFC.2022.3172360","article-title":"Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis","volume":"14","author":"Mai","year":"2022","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113315_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111870","article-title":"Towards robust sentiment analysis with multimodal interaction graph and hybrid contrastive learning","volume":"169","author":"Gong","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113315_bib0029","doi-asserted-by":"crossref","unstructured":"G. Hu, T.-E. Lin, Y. Zhao, G. Lu, Y. Wu, Y. Li, Unimse: Towards unified multimodal sentiment analysis and emotion recognition, (2022), arXiv: 2211.11256.","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"10.1016\/j.patcog.2026.113315_bib0030","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113315_bib0031","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10790","article-title":"Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis","volume":"35","author":"Yu","year":"2021"},{"issue":"1","key":"10.1016\/j.patcog.2026.113315_bib0032","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/TAFFC.2023.3274829","article-title":"Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis","volume":"15","author":"Sun","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113315_bib0033","series-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"3588","article-title":"Multimodal multi-loss fusion network for sentiment analysis","author":"Wu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113315_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111149","article-title":"Co-space representation interaction network for multimodal sentiment analysis","volume":"283","author":"Shi","year":"2024","journal-title":"Knowl. Base. Syst."},{"key":"10.1016\/j.patcog.2026.113315_bib0035","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1601","article-title":"Enriching multimodal sentiment analysis through textual emotional descriptions of visual-audio content","volume":"39","author":"Wu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113315_bib0036","series-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","first-page":"756","article-title":"Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113315_bib0037","series-title":"Findings of the Association for Computational Linguistics","first-page":"14755","article-title":"Knowledge-guided dynamic modality attention fusion framework for multimodal sentiment analysis","author":"Feng","year":"2024"},{"key":"10.1016\/j.patcog.2026.113315_bib0038","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"4400","article-title":"Transformer-based feature reconstruction network for robust multimodal sentiment analysis","author":"Yuan","year":"2021"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326002803?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326002803?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T12:28:46Z","timestamp":1774009726000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326002803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":38,"alternative-id":["S0031320326002803"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113315","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Emotional conflict adaptation for multimodal sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113315","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113315"}}