{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T01:19:57Z","timestamp":1783127997780,"version":"3.54.6"},"reference-count":53,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306184"],"award-info":[{"award-number":["62306184"]}],"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.2026.113922","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T12:33:14Z","timestamp":1778243594000},"page":"113922","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["MEERA: Multimodal experts for evidence routing and sparse LLM adaptation in sentiment analysis"],"prefix":"10.1016","volume":"179","author":[{"given":"Fuqiang","family":"Niu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5783-321X","authenticated-orcid":false,"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.patcog.2026.113922_b1","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1109\/TAFFC.2015.2444846","article-title":"Sentiment analysis: from opinion mining to human-agent interaction","volume":"7","author":"Clavel","year":"2015","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113922_b2","unstructured":"B. Zhang, X. Huang, Z. Huang, H. Huang, B. Zhang, X. Fu, L. Jing, Sentiment interpretable logic tensor network for aspect-term sentiment analysis, in: Proceedings of the 29th International Conference on Computational Linguistics, 2022, pp. 6705\u20136714."},{"key":"10.1016\/j.patcog.2026.113922_b3","doi-asserted-by":"crossref","unstructured":"A. Zadeh, Micro-opinion sentiment intensity analysis and summarization in online videos, in: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, 2015, pp. 587\u2013591.","DOI":"10.1145\/2818346.2823317"},{"issue":"4","key":"10.1016\/j.patcog.2026.113922_b4","doi-asserted-by":"crossref","first-page":"3106","DOI":"10.1109\/TAFFC.2023.3239540","article-title":"Cross-domain aspect-based sentiment classification by exploiting domain-invariant semantic-primary feature","volume":"14","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113922_b5","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.patcog.2026.113922_b6","series-title":"Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content","author":"Wu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113922_b7","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.inffus.2023.02.028","article-title":"Multimodal sentiment analysis based on fusion methods: A survey","volume":"95","author":"Zhu","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113922_b8","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":"13s","key":"10.1016\/j.patcog.2026.113922_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3586075","article-title":"Multimodal sentiment analysis: a survey of methods, trends, and challenges","volume":"55","author":"Das","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.patcog.2026.113922_b10","series-title":"Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016"},{"key":"10.1016\/j.patcog.2026.113922_b11","doi-asserted-by":"crossref","unstructured":"A.B. Zadeh, P.P. Liang, S. Poria, E. Cambria, L.-P. Morency, 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), 2018, pp. 2236\u20132246.","DOI":"10.18653\/v1\/P18-1208"},{"key":"10.1016\/j.patcog.2026.113922_b12","doi-asserted-by":"crossref","unstructured":"A. Zadeh, M. Chen, S. Poria, E. Cambria, L.-P. Morency, Tensor fusion network for multimodal sentiment analysis, in: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017, pp. 1103\u20131114.","DOI":"10.18653\/v1\/D17-1115"},{"key":"10.1016\/j.patcog.2026.113922_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102725","article-title":"AtCAF: Attention-based causality-aware fusion network for multimodal sentiment analysis","volume":"114","author":"Huang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113922_b14","doi-asserted-by":"crossref","unstructured":"A. Zadeh, P.P. Liang, N. Mazumder, S. Poria, E. Cambria, L.-P. Morency, 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":"10.1016\/j.patcog.2026.113922_b15","doi-asserted-by":"crossref","unstructured":"Y.-H.H. Tsai, S. Bai, P.P. Liang, J.Z. Kolter, L.-P. Morency, R. Salakhutdinov, Multimodal transformer for unaligned multimodal language sequences, in: Proceedings of the Conference. Association for Computational Linguistics. Meeting, Vol. 2019, 2019, p. 6558.","DOI":"10.18653\/v1\/P19-1656"},{"key":"10.1016\/j.patcog.2026.113922_b16","doi-asserted-by":"crossref","unstructured":"D. Hazarika, R. Zimmermann, S. Poria, Misa: Modality-invariant and-specific representations for multimodal sentiment analysis, in: Proceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 1122\u20131131.","DOI":"10.1145\/3394171.3413678"},{"key":"10.1016\/j.patcog.2026.113922_b17","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.2026.113922_b18","series-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113922_b19","article-title":"Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning","volume":"37","author":"Cheng","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.patcog.2026.113922_b20","doi-asserted-by":"crossref","DOI":"10.1093\/nsr\/nwae403","article-title":"A survey on multimodal large language models","volume":"11","author":"Yin","year":"2024","journal-title":"Natl. Sci. Rev."},{"key":"10.1016\/j.patcog.2026.113922_b21","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","article-title":"A review of affective computing: From unimodal analysis to multimodal fusion","volume":"37","author":"Poria","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113922_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112277","article-title":"Multimodal sentiment analysis based on label semantic guidance under social links","volume":"171","author":"Liu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113922_b23","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Shen, V.B. Lakshminarasimhan, P.P. Liang, A.B. Zadeh, L.-P. Morency, 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), 2018, pp. 2247\u20132256.","DOI":"10.18653\/v1\/P18-1209"},{"key":"10.1016\/j.patcog.2026.113922_b24","doi-asserted-by":"crossref","unstructured":"W. Yu, H. Xu, Z. Yuan, J. Wu, 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, 2021, pp. 10790\u201310797.","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"10.1016\/j.patcog.2026.113922_b25","doi-asserted-by":"crossref","unstructured":"W. Han, H. Chen, S. Poria, 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, 2021, pp. 9180\u20139192.","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"10.1016\/j.patcog.2026.113922_b26","doi-asserted-by":"crossref","unstructured":"W. Han, H. Chen, A. Gelbukh, A. Zadeh, L.-p. Morency, S. Poria, Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis, in: Proceedings of the 2021 International Conference on Multimodal Interaction, 2021, pp. 6\u201315.","DOI":"10.1145\/3462244.3479919"},{"issue":"3","key":"10.1016\/j.patcog.2026.113922_b27","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.2026.113922_b28","doi-asserted-by":"crossref","unstructured":"H. Sun, H. Wang, J. Liu, Y.-W. Chen, L. Lin, CubeMLP: An MLP-based model for multimodal sentiment analysis and depression estimation, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 3722\u20133729.","DOI":"10.1145\/3503161.3548025"},{"key":"10.1016\/j.patcog.2026.113922_b29","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.2026.113922_b30","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.inffus.2022.11.022","article-title":"AOBERT: All-modalities-in-one BERT for multimodal sentiment analysis","volume":"92","author":"Kim","year":"2023","journal-title":"Inf. Fusion"},{"issue":"2","key":"10.1016\/j.patcog.2026.113922_b31","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/TAFFC.2023.3282410","article-title":"Multi-task momentum distillation for multimodal sentiment analysis","volume":"15","author":"Lin","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113922_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111346","article-title":"TMBL: Transformer-based multimodal binding learning model for multimodal sentiment analysis","volume":"285","author":"Huang","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"10.1016\/j.patcog.2026.113922_b33","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1109\/TAFFC.2024.3423671","article-title":"Multi-level contrastive learning: Hierarchical alleviation of heterogeneity in multimodal sentiment analysis","volume":"16","author":"Fan","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.113922_b34","series-title":"Improving multimodal sentiment analysis via modality optimization and dynamic primary modality selection","author":"Yang","year":"2025"},{"issue":"1","key":"10.1016\/j.patcog.2026.113922_b35","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"key":"10.1016\/j.patcog.2026.113922_b36","unstructured":"N. Shazeer, A. Mirhoseini, K. Maziarz, A. Davis, Q. Le, G. Hinton, J. Dean, Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, in: International Conference on Learning Representations, 2017."},{"issue":"120","key":"10.1016\/j.patcog.2026.113922_b37","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.2026.113922_b38","series-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113922_b39","doi-asserted-by":"crossref","unstructured":"Y. Fang, W. Huang, G. Wan, K. Su, M. Ye, EMOE: Modality-Specific Enhanced Dynamic Emotion Experts, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 14314\u201314324.","DOI":"10.1109\/CVPR52734.2025.01335"},{"key":"10.1016\/j.patcog.2026.113922_b40","doi-asserted-by":"crossref","first-page":"42048","DOI":"10.52202\/079017-1330","article-title":"Mome: Mixture of multimodal experts for generalist multimodal large language models","volume":"37","author":"Shen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113922_b41","doi-asserted-by":"crossref","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113922_b42","unstructured":"Z. Lian, H. Chen, L. Chen, H. Sun, L. Sun, Y. Ren, Z. Cheng, B. Liu, R. Liu, X. Peng, et al., AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models, in: Forty-Second International Conference on Machine Learning."},{"key":"10.1016\/j.patcog.2026.113922_b43","unstructured":"H. Zhang, Z. Li, H. Xu, Y. Zhu, P. Wang, H. Zhu, J. Zhou, J. Zhang, Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark, in: The Thirty-Ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2025."},{"key":"10.1016\/j.patcog.2026.113922_b44","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, 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, 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.patcog.2026.113922_b45","doi-asserted-by":"crossref","unstructured":"Y. Liu, Z. Yuan, H. Mao, Z. Liang, W. Yang, Y. Qiu, T. Cheng, X. Li, H. Xu, K. Gao, Make acoustic and visual cues matter: Ch-sims v2. 0 dataset and av-mixup consistent module, in: Proceedings of the 2022 International Conference on Multimodal Interaction, 2022, pp. 247\u2013258.","DOI":"10.1145\/3536221.3556630"},{"key":"10.1016\/j.patcog.2026.113922_b46","doi-asserted-by":"crossref","unstructured":"W. Rahman, M.K. Hasan, S. Lee, A.B. Zadeh, C. Mao, L.-P. Morency, E. Hoque, Integrating multimodal information in large pretrained transformers, in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 2359\u20132369.","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"10.1016\/j.patcog.2026.113922_b47","article-title":"Cross-modal enhancement network for multimodal sentiment analysis","author":"Wang","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113922_b48","doi-asserted-by":"crossref","unstructured":"H. Zhang, Y. Wang, G. Yin, K. Liu, Y. Liu, T. Yu, Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis, in: The 2023 Conference on Empirical Methods in Natural Language Processing.","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"10.1016\/j.patcog.2026.113922_b49","doi-asserted-by":"crossref","unstructured":"Y. Li, Y. Wang, Z. Cui, Decoupled Multimodal Distilling for Emotion Recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 6631\u20136640.","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"10.1016\/j.patcog.2026.113922_b50","article-title":"Multimodal reaction: Information modulation for cross-modal representation learning","author":"Zeng","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113922_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102031","article-title":"Disentanglement translation network for multimodal sentiment analysis","volume":"102","author":"Zeng","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.113922_b52","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.2026.113922_b53","doi-asserted-by":"crossref","unstructured":"H. Mao, Z. Yuan, H. Xu, W. Yu, Y. Liu, K. Gao, M-SENA: An Integrated Platform for Multimodal Sentiment Analysis, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2022, pp. 204\u2013213.","DOI":"10.18653\/v1\/2022.acl-demo.20"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008873?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008873?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:50:14Z","timestamp":1783126214000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326008873"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":53,"alternative-id":["S0031320326008873"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113922","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":"MEERA: Multimodal experts for evidence routing and sparse LLM adaptation in sentiment analysis","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113922","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":"113922"}}