{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T11:20:43Z","timestamp":1783164043783,"version":"3.54.6"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018556","name":"Science and Technology Program of Suzhou","doi-asserted-by":"publisher","award":["ZXL2023176"],"award-info":[{"award-number":["ZXL2023176"]}],"id":[{"id":"10.13039\/501100018556","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013145","name":"Primary Research and Development Plan of Zhejiang Province","doi-asserted-by":"publisher","award":["2026LDC01028"],"award-info":[{"award-number":["2026LDC01028"]}],"id":[{"id":"10.13039\/501100013145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017529","name":"Major Scientific and Technological Project of Zhejiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017529","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276258"],"award-info":[{"award-number":["62276258"]}],"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":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114019","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T15:15:22Z","timestamp":1780067722000},"page":"114019","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["SENTI: Semantic Enhancement and Relation Propagation Network for multimodal emotion recognition in conversations"],"prefix":"10.1016","volume":"180","author":[{"given":"Jian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peizheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiufeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongming","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9618-8965","authenticated-orcid":false,"given":"Fangyu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114019_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108339","article-title":"Using transformers for multimodal emotion recognition: Taxonomies and state of the art review","volume":"133","author":"Hazmoune","year":"2024","journal-title":"J. Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114019_b2","series-title":"EMNLP","first-page":"2594","article-title":"Icon: Interactive conversational memory network for multimodal emotion detection","author":"Hazarika","year":"2018"},{"key":"10.1016\/j.patcog.2026.114019_b3","article-title":"Exploration meets exploitation: Multitask learning for emotion recognition based on discrete and dimensional models","volume":"235","author":"Tu","year":"2022","journal-title":"KBS"},{"key":"10.1016\/j.patcog.2026.114019_b4","series-title":"ACL","first-page":"2247","article-title":"Efficient Low-rank multimodal fusion with modality-specific factors","author":"Liu","year":"2018"},{"key":"10.1016\/j.patcog.2026.114019_b5","series-title":"ACL","first-page":"481","article-title":"Divide, conquer and combine: Hierarchical feature fusion network with local and global perspectives for multimodal affective computing","author":"Mai","year":"2019"},{"key":"10.1016\/j.patcog.2026.114019_b6","series-title":"ACL","first-page":"14752","article-title":"MultiEMO: An attention-based correlation-aware multimodal fusion framework for emotion recognition in conversations","author":"Shi","year":"2023"},{"key":"10.1016\/j.patcog.2026.114019_b7","series-title":"ACL","first-page":"6267","article-title":"Self-adaptive context and modal-interaction modeling for multimodal emotion recognition","author":"Yang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114019_b8","series-title":"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.patcog.2026.114019_b9","first-page":"1","article-title":"DER-GCN: Dialog and event relation-aware graph convolutional neural network for multimodal dialog emotion recognition","author":"Ai","year":"2024","journal-title":"IEEE TNNLS"},{"key":"10.1016\/j.patcog.2026.114019_b10","series-title":"CVPR","first-page":"21582","article-title":"Vqa-gnn: Reasoning with multimodal knowledge via graph neural networks for visual question answering","author":"Wang","year":"2023"},{"issue":"1","key":"10.1016\/j.patcog.2026.114019_b11","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s12859-023-05622-4","article-title":"A multimodal graph neural network framework for cancer molecular subtype classification","volume":"25","author":"Li","year":"2024","journal-title":"BMC Bioinformatics"},{"key":"10.1016\/j.patcog.2026.114019_b12","series-title":"ACMMM","article-title":"Multimodal emotion recognition calibration in conversations","author":"Tu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114019_b13","first-page":"335","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"J. ELRA"},{"key":"10.1016\/j.patcog.2026.114019_b14","series-title":"ACL","first-page":"527","article-title":"MELD: A multimodal Multi-Party dataset for emotion recognition in conversations","author":"Poria","year":"2019"},{"key":"10.1016\/j.patcog.2026.114019_b15","series-title":"Emotion and intent joint understanding in multimodal conversation: A benchmarking dataset","author":"Liu","year":"2024"},{"issue":"2","key":"10.1016\/j.patcog.2026.114019_b16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3786343","article-title":"A comprehensive survey on multi-modal conversational emotion recognition with deep learning","volume":"44","author":"Shou","year":"2026","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.patcog.2026.114019_b17","series-title":"ACL\/IJCNLP","first-page":"7042","article-title":"DialogueCRN: Contextual reasoning networks for emotion recognition in conversations","author":"Hu","year":"2021"},{"key":"10.1016\/j.patcog.2026.114019_b18","series-title":"AAAI","first-page":"6818","article-title":"Dialoguernn: An attentive rnn for emotion detection in conversations","volume":"Vol. 33","author":"Majumder","year":"2019"},{"key":"10.1016\/j.patcog.2026.114019_b19","first-page":"985","article-title":"CTNet: Conversational transformer network for emotion recognition","volume":"29","author":"Lian","year":"2021","journal-title":"IEEE\/ACM TASLP"},{"key":"10.1016\/j.patcog.2026.114019_b20","series-title":"AAAI","first-page":"13789","article-title":"Dialogxl: All-in-one xlnet for multi-party conversation emotion recognition","volume":"Vol. 35","author":"Shen","year":"2021"},{"key":"10.1016\/j.patcog.2026.114019_b21","article-title":"EmoKEG: Knowledge-enhanced heterogeneous graph for emotion recognition in conversation","author":"Guo","year":"2026","journal-title":"Pattern Recognit.","ISSN":"https:\/\/id.crossref.org\/issn\/0031-3203","issn-type":"print"},{"key":"10.1016\/j.patcog.2026.114019_b22","series-title":"ACL\/IJCNLP","first-page":"1551","article-title":"Directed acyclic graph network for conversational emotion recognition","author":"Shen","year":"2021"},{"key":"10.1016\/j.patcog.2026.114019_b23","article-title":"EmoKEG: Knowledge-enhanced heterogeneous graph for emotion recognition in conversation","author":"Guo","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114019_b24","series-title":"EMNLP","first-page":"3861","article-title":"Multiple Knowledge-Enhanced interactive graph network for multimodal conversational emotion recognition","author":"Tu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114019_b25","series-title":"ACL\/IJCNLP","first-page":"5666","article-title":"MMGCN: Multimodal fusion via deep graph convolution network for emotion recognition in conversation","author":"Hu","year":"2021"},{"issue":"7","key":"10.1016\/j.patcog.2026.114019_b26","first-page":"8419","article-title":"GCNet: Graph completion network for incomplete multimodal learning in conversation","volume":"45","author":"Lian","year":"2023","journal-title":"IEEE TPAMI"},{"key":"10.1016\/j.patcog.2026.114019_b27","series-title":"AAAI","first-page":"19089","article-title":"Adaptive graph learning for multimodal conversational emotion detection","volume":"Vol. 38","author":"Tu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114019_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111340","article-title":"FrameERC: Framelet transform based multimodal graph neural networks for emotion recognition in conversation","volume":"161","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.patcog.2026.114019_b29","doi-asserted-by":"crossref","first-page":"8855","DOI":"10.1038\/s41598-025-89758-8","article-title":"Multi-modal emotion recognition in conversation based on prompt learning with text-audio fusion features","volume":"15","author":"Wu","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.patcog.2026.114019_b30","doi-asserted-by":"crossref","unstructured":"H. Ji, X. Li, M. Li, M. Zhao, C. Gao, Hybrid relational graphs with sentiment-laden semantic alignment for multimodal emotion recognition in conversation, in: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, pp. 2973\u20132981.","DOI":"10.24963\/ijcai.2025\/331"},{"issue":"5","key":"10.1016\/j.patcog.2026.114019_b31","doi-asserted-by":"crossref","first-page":"3020","DOI":"10.1007\/s11263-024-02304-3","article-title":"Noise-resistant multimodal transformer for emotion recognition","volume":"133","author":"Liu","year":"2025","journal-title":"Int. J. Comput. Vis."},{"issue":"5\u20136","key":"10.1016\/j.patcog.2026.114019_b32","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1561\/2200000073","article-title":"Computational optimal transport: With applications to data science","volume":"11","author":"Peyr\u00e9","year":"2019","journal-title":"Found. Trends\u00ae Mach. Learn."},{"issue":"9","key":"10.1016\/j.patcog.2026.114019_b33","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1109\/TPAMI.2016.2615921","article-title":"Optimal transport for domain adaptation","volume":"39","author":"Courty","year":"2016","journal-title":"IEEE TPAMI"},{"key":"10.1016\/j.patcog.2026.114019_b34","series-title":"AAAI","first-page":"3009","article-title":"Unsupervised cross-domain image retrieval via prototypical optimal transport","volume":"Vol. 38","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.114019_b35","first-page":"24074","article-title":"Optimal transport model distributional robustness","volume":"36","author":"Nguyen","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.114019_b36","series-title":"Tokenflow: Rethinking fine-grained cross-modal alignment in vision-language retrieval","author":"Zou","year":"2022"},{"key":"10.1016\/j.patcog.2026.114019_b37","series-title":"NeurIPS","first-page":"439","article-title":"MOC: Multi-modal sentiment analysis via optimal transport and contrastive interactions","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.114019_b38","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s10851-014-0506-3","article-title":"Sliced and radon wasserstein barycenters of measures","volume":"51","author":"Bonneel","year":"2015","journal-title":"J. Math. Imaging Vis."},{"key":"10.1016\/j.patcog.2026.114019_b39","article-title":"Generalized sliced wasserstein distances","volume":"Vol. 32","author":"Kolouri","year":"2019"},{"key":"10.1016\/j.patcog.2026.114019_b40","first-page":"18046","article-title":"Energy-based sliced wasserstein distance","volume":"Vol. 36","author":"Nguyen","year":"2023"},{"key":"10.1016\/j.patcog.2026.114019_b41","series-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.patcog.2026.114019_b42","series-title":"EMNLP","first-page":"2470","article-title":"COSMIC: COmmonSense knowledge for emotion identification in conversations","author":"Ghosal","year":"2020"},{"key":"10.1016\/j.patcog.2026.114019_b43","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.patcog.2026.114019_b44","series-title":"ACMMM","first-page":"1459","article-title":"Opensmile: the munich versatile and fast open-source audio feature extractor","author":"Eyben","year":"2010"},{"key":"10.1016\/j.patcog.2026.114019_b45","series-title":"CVPR","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.patcog.2026.114019_b46","series-title":"Fengshenbang 1.0: Being the foundation of Chinese cognitive intelligence","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.114019_b47","series-title":"NeurIPS","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"Vol. 33","author":"Baevski","year":"2020"},{"key":"10.1016\/j.patcog.2026.114019_b48","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.patcog.2026.114019_b49","series-title":"EMNLP\/IJCNLP","first-page":"154","article-title":"DialogueGCN: A graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.patcog.2026.114019_b50","series-title":"ACL","first-page":"2608","article-title":"Missing modality imagination network for emotion recognition with uncertain missing modalities","author":"Zhao","year":"2021"},{"key":"10.1016\/j.patcog.2026.114019_b51","article-title":"A transformer-based model with self-distillation for multimodal emotion recognition in conversations","author":"Ma","year":"2023","journal-title":"IEEE TMM"},{"key":"10.1016\/j.patcog.2026.114019_b52","series-title":"ACMMM","first-page":"4795","article-title":"DQ-Former: Querying transformer with dynamic modality priority for cognitive-aligned multimodal emotion recognition in conversation","author":"Jing","year":"2024"},{"key":"10.1016\/j.patcog.2026.114019_b53","series-title":"ACMMM","first-page":"1122","article-title":"Misa: Modality-invariant and-specific representations for multimodal sentiment analysis","author":"Hazarika","year":"2020"},{"key":"10.1016\/j.patcog.2026.114019_b54","series-title":"ICASSP","first-page":"7037","article-title":"MM-DFN: Multimodal dynamic fusion network for emotion recognition in conversations","author":"Hu","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009842?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009842?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T10:53:13Z","timestamp":1783162393000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":54,"alternative-id":["S0031320326009842"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114019","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SENTI: Semantic Enhancement and Relation Propagation Network for multimodal emotion recognition in conversations","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114019","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":"114019"}}