{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:16Z","timestamp":1780444816234,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":[[2026,9]]},"DOI":"10.1016\/j.inffus.2026.104289","type":"journal-article","created":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T03:19:04Z","timestamp":1772853544000},"page":"104289","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["TriEMO: Triple semantic alignment based on modality pair contrastive learning graph network for multimodal emotion recognition"],"prefix":"10.1016","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5281-6154","authenticated-orcid":false,"given":"Zehui","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0119-1160","authenticated-orcid":false,"given":"Tong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9862-3293","authenticated-orcid":false,"given":"Kefan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0572-7038","authenticated-orcid":false,"given":"Zhaopeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6981-1948","authenticated-orcid":false,"given":"Huayuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7446-6733","authenticated-orcid":false,"given":"Ting","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104289_bib0001","unstructured":"F. Daneshfar, S. J. Kabudian, Speech Emotion Recognition System by Quaternion Nonlinear Echo State Network, 2021. arXiv: 2111.07234."},{"key":"10.1016\/j.inffus.2026.104289_bib0002","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6818","article-title":"DialogueRNN: an attentive RNN for emotion detection in conversations","author":"Majumder","year":"2019"},{"key":"10.1016\/j.inffus.2026.104289_bib0003","series-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"873","article-title":"Context-Dependent sentiment analysis in user-Generated videos","author":"Poria","year":"2017"},{"key":"10.1016\/j.inffus.2026.104289_bib0004","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)","article-title":"MMGCN: Multimodal fusion via deep graph convolution network for emotion recognition in conversation","author":"Hu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104289_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126427","article-title":"GraphMFT: a graph network based multimodal fusion technique for emotion recognition in conversation","volume":"550","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.inffus.2026.104289_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106764","article-title":"Himul-LGG: a hierarchical decision fusion-based local-global graph neural network for multimodal emotion recognition in conversation","volume":"181","author":"Fu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.inffus.2026.104289_bib0007","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10761","article-title":"Multivariate, multi-Frequency and multimodal: rethinking graph neural networks for emotion recognition in conversation","author":"Chen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104289_bib0008","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4148","article-title":"COGMEN: CONtextualized GNN based multimodal emotion recognition","author":"Joshi","year":"2022"},{"key":"10.1016\/j.inffus.2026.104289_bib0009","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":"1551","article-title":"Directed acyclic graph network for conversational emotion recognition","author":"Shen","year":"2021"},{"key":"10.1016\/j.inffus.2026.104289_bib0010","series-title":"Advances in Neural Information Processing Systems","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020"},{"issue":"8","key":"10.1016\/j.inffus.2026.104289_bib0011","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.70092","article-title":"Multi-Objective manifold representation for opinion mining","volume":"42","author":"Rahman","year":"2025","journal-title":"Expert Syst."},{"key":"10.1016\/j.inffus.2026.104289_bib0012","doi-asserted-by":"crossref","unstructured":"F. Daneshfar, S.J. Kabudian, Speech Emotion Recognition Using Deep Sparse Auto-Encoder Extreme Learning Machine with a New Weighting Scheme and Spectro-Temporal Features Along with Classical Feature Selection and A New Quantum-Inspired Dimension Reduction Method, 2021. arXiv: 2111.07094.","DOI":"10.1109\/ICCKE54056.2021.9721524"},{"key":"10.1016\/j.inffus.2026.104289_bib0013","unstructured":"Z. Feng, T. Qiu, T. Wu, J. Li, H. Xu, T. Han, PreResQ-R1: Towards Fine-Grained Rank-and-Score Reinforcement Learning for Visual Quality Assessment via Preference-Response Disentangled Policy Optimization, 2025. arXiv: 2511.05393."},{"key":"10.1016\/j.inffus.2026.104289_bib0014","series-title":"Proceedings of the 31st International Conference on Computational Linguistics","first-page":"4055","article-title":"A dual contrastive learning framework for enhanced multimodal conversational emotion recognition","author":"Xie","year":"2025"},{"key":"10.1016\/j.inffus.2026.104289_bib0015","series-title":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Enhanced multimodal emotion recognition in conversations via contextual filtering and multi-Frequency graph propagation","author":"Zhao","year":"2025"},{"key":"10.1016\/j.inffus.2026.104289_bib0016","first-page":"1","article-title":"Generalizing to unseen speakers: multimodal emotion recognition in conversations with speaker generalization","author":"Tu","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"10.1016\/j.inffus.2026.104289_bib0017","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/TAFFC.2023.3261279","article-title":"GA2Mif: graph and attention based two-Stage multi-Source information fusion for conversational emotion detection","volume":"15","author":"Li","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104289_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107598","article-title":"Exploration meets exploitation: multitask learning for emotion recognition based on discrete and dimensional models","author":"Tu","year":"2022","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.inffus.2026.104289_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103363","article-title":"A novel hierarchical attention-guided refinement method with EEG assistance for enhancing target speech in a multi-speaker competing environment","volume":"65","author":"Feng","year":"2025","journal-title":"Adv. Eng. Inf."},{"key":"10.1016\/j.inffus.2026.104289_bib0020","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1109\/TASLP.2021.3049898","article-title":"CTNet: Conversational transformer network for emotion recognition","volume":"29","author":"Lian","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"8","key":"10.1016\/j.inffus.2026.104289_bib0021","doi-asserted-by":"crossref","first-page":"5675","DOI":"10.1109\/JBHI.2025.3546019","article-title":"MLST-Net: Multi-Task learning based spatial-Temporal disentanglement scheme for video facial paralysis severity grading","volume":"29","author":"Feng","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"9","key":"10.1016\/j.inffus.2026.104289_bib0022","doi-asserted-by":"crossref","first-page":"6496","DOI":"10.1109\/JBHI.2025.3564981","article-title":"Self-Aware fusion IMU-EMG attention dependence for knee adduction moment estimation during walking","volume":"29","author":"Feng","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.inffus.2026.104289_bib0023","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":"7042","article-title":"DialogueCRN: contextual reasoning networks for emotion recognition in conversations","author":"Hu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104289_bib0024","unstructured":"Z. Feng, C. Zhang, M. Wang, M. Wei, S. Cheng, C. Guan, T. Han, Unveiling Deep Semantic Uncertainty Perception for Language-Anchored Multi-modal Vision-Brain Alignment, 2025. arXiv: 2511.04078."},{"key":"10.1016\/j.inffus.2026.104289_bib0025","series-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","first-page":"1103","article-title":"Tensor fusion network for multimodal sentiment analysis","author":"Zadeh","year":"2017"},{"key":"10.1016\/j.inffus.2026.104289_bib0026","series-title":"Proceedings of the 30th ACM International Conference on Multimedia","first-page":"1642","article-title":"Disentangled representation learning for multimodal emotion recognition","author":"Yang","year":"2022"},{"issue":"1","key":"10.1016\/j.inffus.2026.104289_bib0027","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans. Neural Networks"},{"key":"10.1016\/j.inffus.2026.104289_bib0028","series-title":"International Joint Conference on Natural Language Processing,International Joint Conference on Natural Language Processing","article-title":"DialogueGCN: a graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"issue":"7","key":"10.1016\/j.inffus.2026.104289_bib0029","first-page":"8419","article-title":"GCNet: Graph completion network for incomplete multimodal learning in conversation","volume":"45","author":"Lian","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104289_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103914","article-title":"A novel multi-graph-structure guided human lower-limb physiological load estimation method based on multi-inertial-sensors fusion during walking","volume":"127","author":"Feng","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104289_bib0031","series-title":"Proceedings of the 28th International Conference on Computational Linguistics","first-page":"4153","article-title":"Summarize before aggregate: a global-to-local heterogeneous graph inference network for conversational emotion recognition","author":"Sheng","year":"2020"},{"key":"10.1016\/j.inffus.2026.104289_bib0032","doi-asserted-by":"crossref","first-page":"4298","DOI":"10.1109\/TASLP.2024.3434495","article-title":"Masked graph learning with recurrent alignment for multimodal emotion recognition in conversation","volume":"32","author":"Meng","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.inffus.2026.104289_bib0033","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11002","article-title":"Contrast and generation make BART a good dialogue emotion recognizer","volume":"36","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2026.104289_bib0034","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/TMM.2023.3267295","article-title":"Long dialogue emotion detection based on commonsense knowledge graph guidance","volume":"26","author":"Nie","year":"2024","journal-title":"Trans. Multi."},{"key":"10.1016\/j.inffus.2026.104289_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102590","article-title":"Adversarial alignment and graph fusion via information bottleneck for multimodal emotion recognition in conversations","volume":"112","author":"Shou","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104289_bib0036","series-title":"Proceedings of the 20th Chinese National Conference on Computational Linguistics","first-page":"1218","article-title":"A robustly optimized BERT pre-training approach with post-training","author":"Zhuang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104289_bib0037","series-title":"Proceedings of the 18th ACM International Conference on Multimedia","article-title":"Opensmile","author":"Eyben","year":"2010"},{"key":"10.1016\/j.inffus.2026.104289_bib0038","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.inffus.2026.104289_bib0039","first-page":"1273","article-title":"Less is more: reweighting important spectral graph features for recommendation","author":"Peng","year":"2022"},{"key":"10.1016\/j.inffus.2026.104289_bib0040","unstructured":"K. Oono, T. Suzuki, Graph Neural Networks Exponentially Lose Expressive Power for Node Classification, 2021. https:\/\/arxiv.org\/abs\/1905.10947. arXiv: 1905.10947."},{"key":"10.1016\/j.inffus.2026.104289_bib0041","unstructured":"Q. Li, Z. Han, X.-M. Wu, Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning, 2018, https:\/\/arxiv.org\/abs\/1801.07606. arXiv: 1801.07606."},{"key":"10.1016\/j.inffus.2026.104289_bib0042","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.inffus.2026.104289_bib0043","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","article-title":"MELD: A multimodal multi-Party dataset for emotion recognition in conversations","author":"Poria","year":"2019"},{"key":"10.1016\/j.inffus.2026.104289_bib0044","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","article-title":"Learning what and when to drop","author":"Chen","year":"2021"},{"key":"10.1016\/j.inffus.2026.104289_bib0045","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"9621","article-title":"Multimodal emotion recognition calibration in conversations","author":"Tu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104289_bib0046","series-title":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"A MoE multimodal graph attention network framework for multimodal emotion recognition","author":"Zhang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104289_bib0047","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"5994","article-title":"Multimodal prompt transformer with hybrid contrastive learning for emotion recognition in conversation","author":"Zou","year":"2023"},{"key":"10.1016\/j.inffus.2026.104289_bib0048","series-title":"Advances in Neural Information Processing Systems","article-title":"Stochastic neighbor embedding","volume":"15","author":"Hinton","year":"2002"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526001685?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526001685?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T07:07:39Z","timestamp":1777619259000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526001685"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":48,"alternative-id":["S1566253526001685"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104289","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TriEMO: Triple semantic alignment based on modality pair contrastive learning graph network for multimodal emotion recognition","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104289","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":"104289"}}