{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T10:10:05Z","timestamp":1788689405172,"version":"build-2803163510"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T00:00:00Z","timestamp":1788652800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T00:00:00Z","timestamp":1788652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1007\/s00530-026-02653-8","type":"journal-article","created":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T09:18:21Z","timestamp":1788686301000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Register-augmented attention and self-calibrated fusion for robust multimodal sentiment analysis"],"prefix":"10.1007","volume":"32","author":[{"given":"Bin","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,6]]},"reference":[{"key":"2653_CR1","doi-asserted-by":"crossref","unstructured":"Dhal, D., Mohanty, J.P., Rout, S.S.: A comprehensive survey on multimodal sentiment analysis. In: 2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology (IC-SIT), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/IC-SIT63503.2024.10862066"},{"issue":"5","key":"2653_CR2","doi-asserted-by":"publisher","first-page":"103003","DOI":"10.1016\/j.ipm.2022.103005","volume":"59","author":"JC-W Lin","year":"2022","unstructured":"Lin, J.C.-W., Lv, Q., Yu, D., Srivastava, G., Chen, C.-H.: Optimized scheduling of resource-constraints in projects for smart construction. Inform. Proc. Manag. 59(5), 103003 (2022)","journal-title":"Inform. Proc. Manag."},{"key":"2653_CR3","doi-asserted-by":"crossref","unstructured":"Srivastava, G., Bag, S.: Modern-day marketing concepts based on face recognition and neuro-marketing: a review and future research directions. Benchmarking: An International Journal 31(2), 410\u2013438 (2024)","DOI":"10.1108\/BIJ-09-2022-0588"},{"key":"2653_CR4","doi-asserted-by":"crossref","unstructured":"Tsai, Y.-H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.-P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 6558\u20136569. (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"2653_CR5","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and -specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia (ACM MM), pp. 1122\u20131131. (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"2653_CR6","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.-P.: Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1103\u20131114. (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"2653_CR7","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A., Morency, L.-P.: Efficient low-rank multimodal fusion with modality-specific factors. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 2247\u20132256. (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"2653_CR8","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Yuan, Z., Wu, J.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"2653_CR9","doi-asserted-by":"publisher","first-page":"102725","DOI":"10.1016\/j.inffus.2024.102725","volume":"114","author":"C Huang","year":"2025","unstructured":"Huang, C., Chen, J., Huang, Q., Wang, S., Tu, Y., Huang, X.: Atcaf: attention-based causality-aware fusion network for multimodal sentiment analysis. Information Fusion 114, 102725 (2025)","journal-title":"Information Fusion"},{"issue":"01","key":"2653_CR10","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TAFFC.2025.3606964","volume":"17","author":"J Chen","year":"2026","unstructured":"Chen, J., Zhong, Y., Huang, Q., Huang, C., Jiang, F., Huang, X., Wang, X.: UCMIB-PNS: balancing sufficiency and necessity with probabilistic causality and cross-modal uncertainty in multimodal sentiment analysis. IEEE Trans. Affect. Comput. 17(01), 92\u2013106 (2026)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2653_CR11","doi-asserted-by":"crossref","unstructured":"Huang, C., Lin, Z., Huang, Q., Huang, X., Jiang, F., Chen, J.: H2can: Heterogeneous hypergraph attention network with counterfactual learning for multimodal sentiment analysis. Complex & Intelligent Systems 11(04) (2025)","DOI":"10.1007\/s40747-025-01806-y"},{"key":"2653_CR12","doi-asserted-by":"crossref","unstructured":"Huang, C., Lin, Z., Han, Z., Huang, Q., Jiang, F., Huang, X.: Pamoe-msa: Polarity-aware mixture of experts network for multimodal sentiment analysis. International Journal of Multimedia Information Retrieval 14(01) (2025)","DOI":"10.1007\/s13735-025-00362-y"},{"key":"2653_CR13","doi-asserted-by":"crossref","unstructured":"Chen, J., Huang, Q., Huang, C., Huang, X.: Actual cause-guided adaptive gradient scaling for balanced multimodal sentiment analysis. ACM Trans. Multimedia Comput. Commun. Appl. 21(6) (2025)","DOI":"10.1145\/3736415"},{"key":"2653_CR14","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"2653_CR15","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. In: 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), pp. 4582\u20134597 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"2653_CR16","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045\u20133059. (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"2653_CR17","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers, (2023). arXiv:2309.16588 arXiv preprint"},{"issue":"8","key":"2653_CR18","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"2653_CR19","unstructured":"Wang, K., Zeng, X., Yang, J.: Adaptive gating for multimodal fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3241\u20133250. (2021)"},{"issue":"6","key":"2653_CR20","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MIS.2016.94","volume":"31","author":"A Zadeh","year":"2016","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.-P.: Multimodal sentiment intensity analysis in videos: facial gestures and verbal messages. IEEE Intell. Syst. 31(6), 82\u201388 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"2653_CR21","doi-asserted-by":"crossref","unstructured":"Zadeh, A.B., Liang, P.P., Poria, S., Cambria, E., Morency, L.-P.: Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 2236\u20132246. (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"2653_CR22","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: RoBERTa: a robustly optimized BERT pretraining approach, (2019). arXiv:1907.11692 arXiv preprint"},{"key":"2653_CR23","doi-asserted-by":"crossref","unstructured":"zhang, H., Wang, Y., Yin, G., Liu, K., Liu, Y., Yu, T.: Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. arXiv preprint arXiv:2310.05804 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"2653_CR24","doi-asserted-by":"publisher","first-page":"109259","DOI":"10.1016\/j.patcog.2022.109259","volume":"136","author":"D Wang","year":"2023","unstructured":"Wang, D., Guo, X., Tian, Y., Liu, J., He, L., Luo, X.: TETFN: A text enhanced transformer fusion network for multimodal sentiment analysis. Pattern Recogn. 136, 109259 (2023)","journal-title":"Pattern Recogn."},{"key":"2653_CR25","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Mazumder, N., Poria, S., Cambria, E., Morency, L.-P.: Memory fusion network for multi-view sequential learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"2653_CR26","unstructured":"Mai, S., Xing, S., He, J., Zeng, Y., Hu, H.: Analyzing unaligned multimodal sequence via graph convolution and graph pooling fusion, (2020). arXiv:2011.13572 arXiv preprint"},{"key":"2653_CR27","doi-asserted-by":"crossref","unstructured":"Rahman, W., Hasan, M.K., Lee, S., Zadeh, A.B., Mao, C., Morency, L.-P., Hoque, E.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2359\u20132369. (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"2653_CR28","doi-asserted-by":"crossref","unstructured":"Yang, D., Huang, S., Kuang, H., Du, Y., Zhang, L.: Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1642\u20131651. (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"2653_CR29","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Poria, S.: Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis, (2021). arXiv:2109.00412 arXiv preprint","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"issue":"3","key":"2653_CR30","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1109\/TAFFC.2022.3172360","volume":"14","author":"S Mai","year":"2022","unstructured":"Mai, S., Zeng, Y., Zheng, S., Hu, H.: Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis. IEEE Trans. Affect. Comput. 14(3), 2276\u20132289 (2022)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2653_CR31","doi-asserted-by":"crossref","unstructured":"Wu, Z., Gong, Z., Koo, J., Hirschberg, J.: Multimodal multi-loss fusion network for sentiment analysis. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 3588\u20133602 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.197"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02653-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02653-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02653-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T09:18:25Z","timestamp":1788686305000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02653-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,6]]},"references-count":31,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["2653"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02653-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,6]]},"assertion":[{"value":"16 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"562"}}