{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T23:35:13Z","timestamp":1777592113742,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"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":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10044-026-01671-6","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:25:14Z","timestamp":1777407914000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DHFN: a disentangled hierarchical fusion network for multimodal sentiment analysis"],"prefix":"10.1007","volume":"29","author":[{"given":"Jiajun","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfeng","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"issue":"10","key":"1671_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3656580","volume":"56","author":"PP Liang","year":"2024","unstructured":"Liang PP, Zadeh A, Morency L-P (2024) Foundations and trends in multimodal machine learning: Principles, challenges, and open questions. ACM Comput Surv 56(10):1\u201342. https:\/\/doi.org\/10.1145\/3656580","journal-title":"ACM Comput Surv"},{"issue":"10","key":"1671_CR2","doi-asserted-by":"publisher","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","volume":"45","author":"P Xu","year":"2023","unstructured":"Xu P, Zhu X, Clifton DA (2023) Multimodal learning with transformers: a survey. IEEE Trans Pattern Anal Mach Intell 45(10):12113\u201312132. https:\/\/doi.org\/10.1109\/TPAMI.2023.3275156","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"29","key":"1671_CR3","doi-asserted-by":"publisher","first-page":"21567","DOI":"10.1007\/s00521-023-08941-y","volume":"35","author":"TA Al-Qablan","year":"2023","unstructured":"Al-Qablan TA, Noor MHM, Al-Betar MA, Khader AT (2023) A survey on sentiment analysis and its applications. Neural Comput Appl 35(29):21567\u201321601. https:\/\/doi.org\/10.1007\/s00521-023-08941-y","journal-title":"Neural Comput Appl"},{"key":"1671_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102218","volume":"105","author":"AV Geetha","year":"2024","unstructured":"Geetha AV, Mala T, Priyanka D, Uma E (2024) Multimodal emotion recognition with deep learning: advancements, challenges, and future directions. Inf Fusion 105:102218. https:\/\/doi.org\/10.1016\/j.inffus.2023.102218","journal-title":"Inf Fusion"},{"key":"1671_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.10184","volume":"99","author":"K Ezzameli","year":"2023","unstructured":"Ezzameli K, Mahersia H (2023) Emotion recognition from unimodal to multimodal analysis: A review. Inf Fusion 99:101847. https:\/\/doi.org\/10.1016\/j.inffus.2023.10184","journal-title":"Inf Fusion"},{"key":"1671_CR6","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","volume":"91","author":"A Gandhi","year":"2023","unstructured":"Gandhi A, Adhvaryu K, Poria S, Cambria E, Hussain A (2023) Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Inf Fusion 91:424\u2013444. https:\/\/doi.org\/10.1016\/j.inffus.2022.09.025","journal-title":"Inf Fusion"},{"key":"1671_CR7","doi-asserted-by":"publisher","unstructured":"Zadeh A, Chen M, Poria S, Cambria E, Morency L-P (2017) Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp1103\u20131114. Association for Computational Linguistics, Copenhagen, Denmark. https:\/\/doi.org\/10.18653\/v1\/D17-1115","DOI":"10.18653\/v1\/D17-1115"},{"key":"1671_CR8","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2023) Attention is all you need. https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"1671_CR9","doi-asserted-by":"publisher","unstructured":"Tsai Y-HH, Bai S, Liang PP, Kolter JZ, Morency L-P, Salakhutdinov R (2019) Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 6558\u20136569. Association for Computational Linguistics, Florence, Italy . https:\/\/doi.org\/10.18653\/v1\/P19-1656","DOI":"10.18653\/v1\/P19-1656"},{"key":"1671_CR10","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, Volume 1 (Long and Short Papers), pp 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"1671_CR11","doi-asserted-by":"publisher","unstructured":"Hazarika D, Zimmermann R, Poria S (2020) MISA: modality-invariant and -specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM international conference on multimedia, pp 1122\u20131131. Association for Computing Machinery, Seattle, WA, USA. https:\/\/doi.org\/10.1145\/3394171.3413678","DOI":"10.1145\/3394171.3413678"},{"key":"1671_CR12","doi-asserted-by":"publisher","unstructured":"Yu W, Xu H, Yuan Z, Wu J (2021) 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. https:\/\/doi.org\/10.1609\/aaai.v35i12.17289","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"1671_CR13","doi-asserted-by":"publisher","unstructured":"Yang D, Huang S, Kuang H, Du Y, Zhang L (2022) Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM international conference on multimedia, pp 1642\u20131651. https:\/\/doi.org\/10.1145\/3503161.3547754","DOI":"10.1145\/3503161.3547754"},{"key":"1671_CR14","doi-asserted-by":"publisher","unstructured":"Li Y, Wang Y, Cui Z (2023) Decoupled multimodal distilling for emotion recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6631\u20136640.https:\/\/doi.org\/10.1109\/CVPR52729.2023.00641","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"1671_CR15","doi-asserted-by":"crossref","unstructured":"Yang D, Chen Z, Wang Y, Wang S, Li M, Liu S, Zhao X, Huang S, Dong Z, Zhai P, Zhang L (2023) Context de-confounded emotion recognition. https:\/\/arxiv.org\/abs\/2303.11921","DOI":"10.1109\/CVPR52729.2023.01822"},{"issue":"8","key":"1671_CR16","doi-asserted-by":"publisher","first-page":"5325","DOI":"10.1109\/TPAMI.2024.3366349","volume":"46","author":"S Hu","year":"2024","unstructured":"Hu S, Lou Z, Yan X, Ye Y (2024) A survey on information bottleneck. IEEE Trans Pattern Anal Mach Intell 46(8):5325\u20135344. https:\/\/doi.org\/10.1109\/TPAMI.2024.3366349","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1671_CR17","doi-asserted-by":"publisher","unstructured":"Han W, Chen H, Poria S (2021) Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Proceedings of the 2021 conference on empirical methods in natural language processing, pp 9180\u20139192. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic . https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.723","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"1671_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111346","volume":"285","author":"J Huang","year":"2024","unstructured":"Huang J, Zhou J, Tang Z, Lin J, Chen CY-C (2024) Tmbl: transformer-based multimodal binding learning model for multimodal sentiment analysis. Knowl-Based Syst 285:111346. https:\/\/doi.org\/10.1016\/j.knosys.2023.111346","journal-title":"Knowl-Based Syst"},{"issue":"7","key":"1671_CR19","doi-asserted-by":"publisher","first-page":"1978","DOI":"10.19734\/j.issn.1001-3695.2024.11.0487","volume":"42","author":"J Wang","year":"2025","unstructured":"Wang J, Zhao X, Wang C, Zhang S, Zhao S (2025) Deep feature interaction and hierarchical multimodal fusion for emotion recognition. Appl Res Comput 42(7):1978\u20131985. https:\/\/doi.org\/10.19734\/j.issn.1001-3695.2024.11.0487","journal-title":"Appl Res Comput"},{"key":"1671_CR20","doi-asserted-by":"publisher","first-page":"9044","DOI":"10.1109\/TMM.2025.3613116","volume":"27","author":"Y Zhuang","year":"2025","unstructured":"Zhuang Y, Bai W, Zhang Y, Deng J, Hu Z, Zhang X, Ren F (2025) Multi-level contrastive learning for multimodal sentiment analysis. IEEE Trans Multimed 27:9044\u20139058. https:\/\/doi.org\/10.1109\/TMM.2025.3613116","journal-title":"IEEE Trans Multimed"},{"issue":"6","key":"1671_CR21","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 (2016) Multimodal sentiment intensity analysis in videos: facial gestures and verbal messages. IEEE Intell Syst 31(6):82\u201388. https:\/\/doi.org\/10.1109\/MIS.2016.94","journal-title":"IEEE Intell Syst"},{"key":"1671_CR22","doi-asserted-by":"publisher","unstructured":"Zadeh AB, Liang PP, Poria S, Cambria E, Morency L-P (2018) 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 (Volume 1: Long Papers), pp 2236\u20132246. Association for Computational Linguistics, Melbourne, Australia. https:\/\/doi.org\/10.18653\/v1\/P18-1208","DOI":"10.18653\/v1\/P18-1208"},{"key":"1671_CR23","doi-asserted-by":"publisher","unstructured":"Liu Z, Shen Y, Lakshminarasimhan VB, Liang PP, Zadeh AB, Morency L-P (2018) Efficient low-rank multimodal fusion with modality-specific factors. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp 2247\u20132256. Association for Computational Linguistics, Melbourne, Australia . https:\/\/doi.org\/10.18653\/v1\/P18-1209","DOI":"10.18653\/v1\/P18-1209"},{"key":"1671_CR24","unstructured":"Jaegle A, Gimeno F, Brock A, Zisserman A, Vinyals O, Carreira J (2021) Perceiver: general perception with iterative attention. https:\/\/arxiv.org\/abs\/2103.03206"},{"key":"1671_CR25","doi-asserted-by":"publisher","unstructured":"Rahman W, Hasan MK, Lee S, Zadeh A, Mao C, Morency L-P, Hoque E (2020) Integrating multimodal information in large pretrained transformers. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 2359\u20132369. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.214","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"1671_CR26","doi-asserted-by":"publisher","unstructured":"Huang J, Tao J, Liu B, Lian Z, Niu M (2020) Multimodal transformer fusion for continuous emotion recognition. In: ICASSP 2020 - 2020 ieee international conference on acoustics, speech and signal processing (ICASSP), pp 3507\u20133511. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053762","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"1671_CR27","doi-asserted-by":"publisher","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 (2025) Atcaf: attention-based causality-aware fusion network for multimodal sentiment analysis. Inf Fusion 114:102725. https:\/\/doi.org\/10.1016\/j.inffus.2024.102725","journal-title":"Inf Fusion"},{"key":"1671_CR28","doi-asserted-by":"publisher","DOI":"10.1145\/3736415","author":"J Chen","year":"2025","unstructured":"Chen J, Huang Q, Huang C, Huang X (2025) Actual cause-guided adaptive gradient scaling for balanced multimodal sentiment analysis. ACM Trans Multimed Comput Commun Appl. https:\/\/doi.org\/10.1145\/3736415","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"1671_CR29","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2024.01508119","author":"X Zhao","year":"2024","unstructured":"Zhao X, Wang M, Tan Y, Wang X (2024) TGMoE: a text guided mixture-of-experts model for multimodal sentiment analysis. Int J Adv Comput Sci Appl. https:\/\/doi.org\/10.14569\/IJACSA.2024.01508119","journal-title":"Int J Adv Comput Sci Appl"},{"issue":"1","key":"1671_CR30","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1109\/taffc.2023.3274829","volume":"15","author":"L Sun","year":"2024","unstructured":"Sun L, Lian Z, Liu B, Tao J (2024) Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. IEEE Trans Affect Comput 15(1):309\u2013325. https:\/\/doi.org\/10.1109\/taffc.2023.3274829","journal-title":"IEEE Trans Affect Comput"},{"key":"1671_CR31","doi-asserted-by":"publisher","unstructured":"Yuan Z, Li W, Xu H, Yu W (2021) Transformer-based feature reconstruction network for robust multimodal sentiment analysis. In: Proceedings of the 29th ACM international conference on multimedia, pp 4400\u20134407. https:\/\/doi.org\/10.1145\/3474085.3475585","DOI":"10.1145\/3474085.3475585"},{"key":"1671_CR32","doi-asserted-by":"publisher","unstructured":"Zhang H, Wang Y, Yin G, Liu K, Liu Y, Yu T (2023) Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. In: Proceedings of the 2023 conference on empirical methods in natural language processing, pp 756\u2013767 . https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.49","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"1671_CR33","doi-asserted-by":"crossref","unstructured":"Wang W, Ding L, Shen L, Luo Y, Hu H, Tao D (2024) WisdoM: improving multimodal sentiment analysis by fusing contextual world knowledge. https:\/\/arxiv.org\/abs\/2401.06659","DOI":"10.1145\/3664647.3681403"},{"issue":"12","key":"1671_CR34","doi-asserted-by":"publisher","first-page":"9102","DOI":"10.1109\/TPAMI.2024.3420239","volume":"46","author":"Y Zhu","year":"2024","unstructured":"Zhu Y, Wu Y, Sebe N, Yan Y (2024) Vision + X: a survey on multimodal learning in the light of data. IEEE Trans Pattern Anal Mach Intell 46(12):9102\u20139122. https:\/\/doi.org\/10.1109\/TPAMI.2024.3420239","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"1671_CR35","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s13735-025-00362-y","volume":"14","author":"C Huang","year":"2025","unstructured":"Huang C, Lin Z, Han Z, Huang Q, Jiang F, Huang X (2025) Pamoe-msa: Polarity-aware mixture of experts network for multimodal sentiment analysis. International Journal of Multimedia Information Retrieval 14(1):7. https:\/\/doi.org\/10.1007\/s13735-025-00362-y","journal-title":"International Journal of Multimedia Information Retrieval"},{"key":"1671_CR36","doi-asserted-by":"publisher","unstructured":"Huang C, Lin Z, Huang Q, Huang X, Jiang F, Chen J (2025) $$\\text{ H}^2\\text{ CAN }$$: heterogeneous hypergraph attention network with counterfactual learning for multimodal sentiment analysis. Complex Intell Syst 11(4):196. https:\/\/doi.org\/10.1007\/s40747-025-01806-y","DOI":"10.1007\/s40747-025-01806-y"},{"key":"1671_CR37","doi-asserted-by":"crossref","unstructured":"Xiao L, Mao R, Zhao S, Lin Q, Jia Y, He L, Cambria E (2025) Exploring cognitive and aesthetic causality for multimodal aspect-based sentiment analysis. https:\/\/arxiv.org\/abs\/2504.15848","DOI":"10.1109\/TAFFC.2025.3565506"},{"key":"1671_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102304","volume":"106","author":"L Xiao","year":"2024","unstructured":"Xiao L, Wu X, Xu J, Li W, Jin C, He L (2024) Atlantis: aesthetic-oriented multiple granularities fusion network for joint multimodal aspect-based sentiment analysis. Inf Fusion 106:102304. https:\/\/doi.org\/10.1016\/j.inffus.2024.102304","journal-title":"Inf Fusion"},{"issue":"6","key":"1671_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103508","volume":"60","author":"L Xiao","year":"2023","unstructured":"Xiao L, Wu X, Yang S, Xu J, Zhou J, He L (2023) Cross-modal fine-grained alignment and fusion network for multimodal aspect-based sentiment analysis. Inf Process Manag 60(6):103508. https:\/\/doi.org\/10.1016\/j.ipm.2023.103508","journal-title":"Inf Process Manag"},{"key":"1671_CR40","doi-asserted-by":"publisher","unstructured":"Xiao L, Mao R, Zhang X, He L, Cambria E (2024) Vanessa: visual connotation and aesthetic attributes understanding network for multimodal aspect-based sentiment analysis. In: Findings of the association for computational linguistics: EMNLP 2024, pp 1486\u201311500. Association for Computational Linguistics, Miami, Florida, USA. https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.671","DOI":"10.18653\/v1\/2024.findings-emnlp.671"},{"key":"1671_CR41","doi-asserted-by":"crossref","unstructured":"Xiao L, Wu X, Wu W, Yang J, He L (2022) Multi-channel attentive graph convolutional network with sentiment fusion for multimodal sentiment analysis.https:\/\/arxiv.org\/abs\/2201.10274","DOI":"10.1109\/ICASSP43922.2022.9747542"},{"key":"1671_CR42","doi-asserted-by":"publisher","unstructured":"Xiao L, Zhou E, Wu X, Yang S, Ma T, He L (2022) Adaptive multi-feature extraction graph convolutional networks for multimodal target sentiment analysis. In: 2022 IEEE international conference on multimedia and expo (ICME), pp 1-6. https:\/\/doi.org\/10.1109\/ICME52920.2022.9860020","DOI":"10.1109\/ICME52920.2022.9860020"},{"key":"1671_CR43","doi-asserted-by":"publisher","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815\u2013823 . https:\/\/doi.org\/10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01671-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01671-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01671-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:25:17Z","timestamp":1777407917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01671-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,28]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1671"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01671-6","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,28]]},"assertion":[{"value":"31 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"94"}}