{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:09:37Z","timestamp":1781280577509,"version":"3.54.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104467","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:22:42Z","timestamp":1778602962000},"page":"104467","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["UTIM: An uncertainty-aware taylor interaction network for robust multimodal sentiment analysis"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1151-5134","authenticated-orcid":false,"given":"Yanlian","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0344-3080","authenticated-orcid":false,"given":"Yue","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5824-9488","authenticated-orcid":false,"given":"Guangdong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3764-2640","authenticated-orcid":false,"given":"Xiaofang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104467_bib0001","series-title":"International Conference on Machine Learning","first-page":"1298","article-title":"Data2vec: a general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022"},{"key":"10.1016\/j.inffus.2026.104467_bib0002","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: a review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104467_bib0003","series-title":"Proc. Interspeech 2024","first-page":"4658","article-title":"Lora-mer: low-rank adaptation of pre-trained speech models for multimodal emotion recognition using mutual information","author":"Cai","year":"2024"},{"key":"10.1016\/j.inffus.2026.104467_bib0004","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.inffus.2019.02.010","article-title":"Embracenet: a robust deep learning architecture for multimodal classification","volume":"51","author":"Choi","year":"2019","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104467_bib0005","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":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104467_bib0006","doi-asserted-by":"crossref","unstructured":"D. Hazarika, Y. Li, B. Cheng, S. Zhao, R. Zimmermann, S. Poria, 2022. Analyzing modality robustness in multimodal sentiment analysis. arXiv: 2205.15465.","DOI":"10.18653\/v1\/2022.naacl-main.50"},{"key":"10.1016\/j.inffus.2026.104467_bib0007","series-title":"Proceedings of the 28th 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.inffus.2026.104467_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.inffus.2026.104467_bib0009","article-title":"Robust multimodal sentiment analysis via double information bottleneck","volume":"129","author":"Huang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104467_bib0010","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10074","article-title":"A unified self-distillation framework for multimodal sentiment analysis with uncertain missing modalities","author":"Li","year":"2024"},{"key":"10.1016\/j.inffus.2026.104467_bib0011","first-page":"28515","article-title":"Toward robust incomplete multimodal sentiment analysis via hierarchical representation learning","volume":"37","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104467_bib0012","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1162\/tacl_a_00628","article-title":"Missmodal: increasing robustness to missing modality in multimodal sentiment analysis","volume":"11","author":"Lin","year":"2023","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.inffus.2026.104467_bib0013","unstructured":"Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, V. Stoyanov, 2019. Roberta: a robustly optimized bert pretraining approach. arXiv: 1907.11692."},{"key":"10.1016\/j.inffus.2026.104467_bib0014","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2247","article-title":"Efficient low-rank multimodal fusion with modality-specific factors","author":"Liu","year":"2018"},{"key":"10.1016\/j.inffus.2026.104467_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101973","article-title":"Modality translation-based multimodal sentiment analysis under uncertain missing modalities","volume":"101","author":"Liu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104467_bib0016","first-page":"7047","article-title":"Predictive uncertainty estimation via prior networks","volume":"31","author":"Malinin","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104467_bib0017","doi-asserted-by":"crossref","unstructured":"H. Mao, Z. Yuan, H. Xu, W. Yu, Y. Liu, K. Gao, 2022. M-sena: an integrated platform for multimodal sentiment analysis. arXiv: 2203.12441.","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"10.1016\/j.inffus.2026.104467_bib0018","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"16458","article-title":"Robust-msa: understanding the impact of modality noise on multimodal sentiment analysis","author":"Mao","year":"2023"},{"key":"10.1016\/j.inffus.2026.104467_bib0019","unstructured":"A.v.d. Oord, Y. Li, O. Vinyals, 2018. Representation learning with contrastive predictive coding. arXiv: 1807.03748."},{"key":"10.1016\/j.inffus.2026.104467_bib0020","doi-asserted-by":"crossref","first-page":"662","DOI":"10.3390\/electronics13030662","article-title":"Hybrid uncertainty calibration for multimodal sentiment analysis","volume":"13","author":"Pan","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.inffus.2026.104467_bib0021","article-title":"Evidential deep learning to quantify classification uncertainty","volume":"31","author":"Sensoy","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104467_bib0022","series-title":"Proceedings of the ACM on Web Conference 2025","first-page":"2540","article-title":"Multimodal taylor series network for misinformation detection","author":"Sun","year":"2025"},{"key":"10.1016\/j.inffus.2026.104467_bib0023","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.inffus.2026.104467_bib0024","series-title":"Proceedings of the Conference. Association for Computational Linguistics. Meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","author":"Tsai","year":"2019"},{"key":"10.1016\/j.inffus.2026.104467_bib0025","first-page":"17117","article-title":"Incomplete multimodality-diffused emotion recognition","volume":"36","author":"Wang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104467_bib0026","doi-asserted-by":"crossref","unstructured":"Y. Wu, Y. Zhao, H. Yang, S. Chen, B. Qin, X. Cao, W. Zhao, 2022. Sentiment word aware multimodal refinement for multimodal sentiment analysis with asr errors. arXiv: 2203.00257.","DOI":"10.18653\/v1\/2022.findings-acl.109"},{"key":"10.1016\/j.inffus.2026.104467_bib0027","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"3588","article-title":"Multimodal multi-loss fusion network for sentiment analysis","author":"Wu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104467_bib0028","doi-asserted-by":"crossref","first-page":"7657","DOI":"10.1109\/TCSVT.2024.3376564","article-title":"Trustworthy multimodal fusion for sentiment analysis in ordinal sentiment space","volume":"34","author":"Xie","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104467_bib0029","unstructured":"J. Xin, S. Yun, J. Peng, I. Choi, J.L. Ballard, T. Chen, Q. Long, 2025. I2moe: interpretable multimodal interaction-aware mixture-of-experts. arXiv: 2505.19190."},{"key":"10.1016\/j.inffus.2026.104467_bib0030","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"7617","article-title":"Confede: contrastive feature decomposition for multimodal sentiment analysis","author":"Yang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104467_bib0031","series-title":"Proceedings of the 58th 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.inffus.2026.104467_bib0032","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","author":"Yu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104467_bib0033","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"},{"key":"10.1016\/j.inffus.2026.104467_bib0034","doi-asserted-by":"crossref","unstructured":"A. Zadeh, M. Chen, S. Poria, E. Cambria, L.P. Morency, 2017. Tensor fusion network for multimodal sentiment analysis. arXiv: 1707.07250.","DOI":"10.18653\/v1\/D17-1115"},{"key":"10.1016\/j.inffus.2026.104467_bib0035","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Memory fusion network for multi-view sequential learning","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.inffus.2026.104467_bib0036","unstructured":"A. Zadeh, R. Zellers, E. Pincus, L.P. Morency, 2016. Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv: 1606.06259."},{"key":"10.1016\/j.inffus.2026.104467_bib0037","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","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.inffus.2026.104467_bib0038","first-page":"55943","article-title":"Towards robust multimodal sentiment analysis with incomplete data","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104467_bib0039","series-title":"Proceedings of the 31st International Conference on Computational Linguistics","first-page":"4611","article-title":"Modal feature optimization network with prompt for multimodal sentiment analysis","author":"Zhang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104467_bib0040","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11Th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"2608","article-title":"Missing modality imagination network for emotion recognition with uncertain missing modalities","author":"Zhao","year":"2021"},{"key":"10.1016\/j.inffus.2026.104467_bib0041","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"1800","article-title":"Glomo: global-local modal fusion for multimodal sentiment analysis","author":"Zhuang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104467_bib0042","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"833","article-title":"Acformer: an aligned and compact transformer for multimodal sentiment analysis","author":"Zong","year":"2023"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003465?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003465?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:54:58Z","timestamp":1781279698000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":42,"alternative-id":["S1566253526003465"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104467","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"UTIM: An uncertainty-aware taylor interaction network for robust multimodal sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104467","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104467"}}