{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:10:48Z","timestamp":1780495848817,"version":"3.54.1"},"reference-count":52,"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\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M781481"],"award-info":[{"award-number":["2025M781481"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236006"],"award-info":[{"award-number":["62236006"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113517","type":"journal-article","created":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T15:45:24Z","timestamp":1774194324000},"page":"113517","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["AlignMamba-2: Enhancing multimodal fusion and sentiment analysis with modality-aware Mamba"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5790-708X","authenticated-orcid":false,"given":"Yan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-9515","authenticated-orcid":false,"given":"Yifei","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8564-0346","authenticated-orcid":false,"given":"Xiangyuan","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1670-1368","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7164-5840","authenticated-orcid":false,"given":"Haifeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-8499","authenticated-orcid":false,"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113517_bib0001","unstructured":"A. Zadeh, R. Zellers, E. Pincus, L.-P. Morency, Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos, arXiv: 1606.06259 (2016)."},{"key":"10.1016\/j.patcog.2026.113517_bib0002","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"},{"issue":"1","key":"10.1016\/j.patcog.2026.113517_bib0003","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1109\/TAFFC.2024.3440924","article-title":"Aves: an audio-visual emotion stream dataset for temporal emotion detection","volume":"16","author":"Li","year":"2024","journal-title":"IEEE Trans. Affect Comput."},{"key":"10.1016\/j.patcog.2026.113517_bib0004","unstructured":"L.H. Li, M. Yatskar, D. Yin, C.-J. Hsieh, K.-W. Chang, Visualbert: A simple and performant baseline for vision and language, (2019). arXiv: 1908.03557."},{"key":"10.1016\/j.patcog.2026.113517_bib0005","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"Vilt: vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.patcog.2026.113517_bib0006","unstructured":"H. Liu, C. Li, Q. Wu, Y.J. Lee, Visual Instruction Tuning, (2023). arXiv: 2304.08485."},{"key":"10.1016\/j.patcog.2026.113517_bib0007","series-title":"Proceedings of the Conference. Association for Computational Linguistics. Meeting","first-page":"6558","article-title":"Multimodal transformer for unaligned multimodal language sequences","volume":"2019","author":"Tsai","year":"2019"},{"key":"10.1016\/j.patcog.2026.113517_bib0008","doi-asserted-by":"crossref","first-page":"2213","DOI":"10.1109\/TMM.2022.3144885","article-title":"Multi-channel weight-sharing autoencoder based on cascade multi-head attention for multimodal emotion recognition","volume":"25","author":"Zheng","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113517_bib0009","article-title":"Multimodal spatiotemporal semisupervised transformer network for video-Based group-Level emotion recognition","author":"Huang","year":"2025","journal-title":"IEEE Trans. Comput. Social Syst."},{"key":"10.1016\/j.patcog.2026.113517_bib0010","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.2026.113517_bib0011","article-title":"Appearance-and relation-aware parallel graph attention fusion network for facial expression recognition","author":"Li","year":"2025","journal-title":"IEEE Trans. Affect Comput."},{"key":"10.1016\/j.patcog.2026.113517_bib0012","unstructured":"A. Gu, I. Johnson, K. Goel, K. Saab, T. Dao, A. Rudra, C. R\u00e9, Combining recurrent, convolutional, and continuous-time models with linear state space layers, Adv. Neural Inf. Process. Syst. 34 (2021) 572\u2013585."},{"key":"10.1016\/j.patcog.2026.113517_bib0013","unstructured":"A. Gu, T. Dao, Mamba: Linear-time sequence modeling with selective state spaces, (2023). arXiv: 2312.00752."},{"key":"10.1016\/j.patcog.2026.113517_bib0014","unstructured":"Y. Qiao, Z. Yu, L. Guo, S. Chen, Z. Zhao, M. Sun, Q. Wu, J. Liu, Vl-mamba: Exploring state space models for multimodal learning, (2024). arXiv: 2403.13600."},{"key":"10.1016\/j.patcog.2026.113517_bib0015","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10421","article-title":"Cobra: extending mamba to multi-modal large language model for efficient inference","volume":"39","author":"Zhao","year":"2025"},{"key":"10.1016\/j.patcog.2026.113517_bib0016","doi-asserted-by":"crossref","unstructured":"X. He, K. Cao, K. Yan, R. Li, C. Xie, J. Zhang, M. Zhou, Pan-mamba: Effective pan-sharpening with state space model, arXiv: 2402.12192(2024).","DOI":"10.1016\/j.inffus.2024.102779"},{"key":"10.1016\/j.patcog.2026.113517_bib0017","unstructured":"W. Dong, H. Zhu, S. Lin, X. Luo, Y. Shen, X. Liu, J. Zhang, G. Guo, B. Zhang, Fusion-mamba for cross-modality object detection, arXiv: 2404.09146(2024)."},{"key":"10.1016\/j.patcog.2026.113517_bib0018","article-title":"Multi-modal mamba framework for RGB-T crowd counting with linear complexity","author":"Gan","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113517_bib0019","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"24774","article-title":"Alignmamba: enhancing multimodal mamba with local and global cross-modal alignment","author":"Li","year":"2025"},{"issue":"12","key":"10.1016\/j.patcog.2026.113517_bib0020","doi-asserted-by":"crossref","first-page":"7121","DOI":"10.1109\/TCSVT.2023.3275814","article-title":"Cross-level multi-modal features learning with transformer for rgb-d object recognition","volume":"33","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"9","key":"10.1016\/j.patcog.2026.113517_bib0021","first-page":"1","article-title":"Multimodal PEAR chain-of-thought reasoning for multimodal sentiment analysis","volume":"20","author":"Li","year":"2025","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.patcog.2026.113517_bib0022","first-page":"32897","article-title":"Vlmo: unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113517_bib0023","series-title":"International Conference on Learning Representations","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2021"},{"issue":"120","key":"10.1016\/j.patcog.2026.113517_bib0024","first-page":"1","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113517_bib0025","unstructured":"D. Dai, C. Deng, C. Zhao, R.X. Xu, H. Gao, D. Chen, J. Li, W. Zeng, X. Yu, Y. Wu, et al., Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models, arXiv: 2401.06066(2024a)."},{"issue":"10","key":"10.1016\/j.patcog.2026.113517_bib0026","doi-asserted-by":"crossref","first-page":"9910","DOI":"10.1109\/TCSVT.2024.3405406","article-title":"Multimodal decoupled distillation graph neural network for emotion recognition in conversation","volume":"34","author":"Dai","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113517_bib0027","article-title":"Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis","author":"Mai","year":"2022","journal-title":"IEEE Trans. Affect Comput."},{"key":"10.1016\/j.patcog.2026.113517_bib0028","article-title":"Multi-Task momentum distillation for multimodal sentiment analysis","author":"Lin","year":"2023","journal-title":"IEEE Trans. Affect Comput."},{"key":"10.1016\/j.patcog.2026.113517_bib0029","series-title":"Proceedings of the 31St ACM International Conference on Multimedia","first-page":"6063","article-title":"Towards adaptable graph representation learning: an adaptive multi-graph contrastive transformer","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113517_bib0030","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8992","article-title":"Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis","volume":"34","author":"Sun","year":"2020"},{"key":"10.1016\/j.patcog.2026.113517_bib0031","series-title":"Topics in optimal transportation","volume":"58","author":"Villani","year":"2021"},{"key":"10.1016\/j.patcog.2026.113517_bib0032","doi-asserted-by":"crossref","first-page":"39090","DOI":"10.52202\/068431-2833","article-title":"Otkge: multi-modal knowledge graph embeddings via optimal transport","volume":"35","author":"Cao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113517_bib0033","article-title":"Sinkhorn distances: lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.patcog.2026.113517_bib0034","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"The J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113517_bib0035","series-title":"European Conference on Computer Vision","first-page":"746","article-title":"Indoor segmentation and support inference from rgbd images","author":"Silberman","year":"2012"},{"key":"10.1016\/j.patcog.2026.113517_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26876","article-title":"Embracing unimodal aleatoric uncertainty for robust multimodal fusion","author":"Gao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113517_bib0037","series-title":"International Conference on Multimedia Modeling","first-page":"15","article-title":"Sentiment analysis on multi-view social data","author":"Niu","year":"2016"},{"key":"10.1016\/j.patcog.2026.113517_bib0038","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.patcog.2026.113517_bib0039","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"},{"key":"10.1016\/j.patcog.2026.113517_bib0040","doi-asserted-by":"crossref","unstructured":"W. Han, H. Chen, S. Poria, Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis, arXiv: 2109.00412(2021).","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"10.1016\/j.patcog.2026.113517_bib0041","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.patcog.2026.113517_bib0042","series-title":"Proceedings of the 32Nd ACM International Conference on Multimedia","first-page":"9650","article-title":"Enhanced experts with uncertainty-aware routing for multimodal sentiment analysis","author":"Gao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113517_bib0043","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12186","article-title":"Multimodal token fusion for vision transformers","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113517_bib0044","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3435561","article-title":"Asynchronous multimodal video sequence fusion via learning modality-exclusive and-agnostic representations","author":"Yang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113517_bib0045","series-title":"International Conference on Machine Learning","first-page":"21753","article-title":"Geminifusion: efficient pixel-wise multimodal fusion for vision transformer","author":"Jia","year":"2024"},{"key":"10.1016\/j.patcog.2026.113517_bib0046","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"},{"key":"10.1016\/j.patcog.2026.113517_bib0047","article-title":"MDKAT: Multimodal decoupling with knowledge aggregation and transfer for video emotion recognition","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113517_bib0048","doi-asserted-by":"crossref","first-page":"59808","DOI":"10.52202\/079017-1910","article-title":"Coupled mamba: enhanced multimodal fusion with coupled state space model","volume":"37","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113517_bib0049","series-title":"2025IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"1734","article-title":"Sigma: siamese mamba network for multi-modal semantic segmentation","author":"Wan","year":"2025"},{"key":"10.1016\/j.patcog.2026.113517_bib0050","series-title":"International Conference on Learning Representations","article-title":"Trusted multi-View classification","author":"Han","year":"2021"},{"key":"10.1016\/j.patcog.2026.113517_bib0051","series-title":"International Conference on Machine Learning","first-page":"41753","article-title":"Provable dynamic fusion for low-quality multimodal data","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113517_bib0052","doi-asserted-by":"crossref","DOI":"10.1145\/3744648","article-title":"A multimodal semantic fusion network with cross-Modal alignment for multimodal sentiment analysis","author":"Zhang","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004838?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004838?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:12:46Z","timestamp":1780492366000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":52,"alternative-id":["S0031320326004838"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113517","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"AlignMamba-2: Enhancing multimodal fusion and sentiment analysis with modality-aware Mamba","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113517","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":"113517"}}