{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T22:06:37Z","timestamp":1779228397421,"version":"3.51.4"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100017938","name":"Hebei Provincial Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017938","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008238","name":"Hebei Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["21373802D"],"award-info":[{"award-number":["21373802D"]}],"id":[{"id":"10.13039\/501100008238","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008238","name":"Hebei Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["23561007D"],"award-info":[{"award-number":["23561007D"]}],"id":[{"id":"10.13039\/501100008238","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.csl.2026.101989","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T09:02:16Z","timestamp":1775898136000},"page":"101989","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["GNN\u2013Transformer cross-view contrastive learning for multimodal conversational emotion recognition"],"prefix":"10.1016","volume":"100","author":[{"given":"Yujie","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2674-3721","authenticated-orcid":false,"given":"Yunfeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengwei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2026.101989_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124852","article-title":"A systematic review of trimodal affective computing approaches: Text, audio, and visual integration in emotion recognition and sentiment analysis","volume":"255","author":"Al-Saadawi","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.csl.2026.101989_b2","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.csl.2026.101989_b3","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15745","article-title":"Exploring simple siamese representation learning","author":"Chen","year":"2020"},{"key":"10.1016\/j.csl.2026.101989_b4","series-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.csl.2026.101989_b5","article-title":"Opensmile: the munich versatile and fast open-source audio feature extractor","author":"Eyben","year":"2010","journal-title":"Proc. the 18th ACM Int. Conf. Multimed."},{"key":"10.1016\/j.csl.2026.101989_b6","series-title":"Findings","article-title":"COSMIC: COmmonSense knowledge for emotion identification in conversations","author":"Ghosal","year":"2020"},{"key":"10.1016\/j.csl.2026.101989_b7","series-title":"Conference on Empirical Methods in Natural Language Processing","article-title":"Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.csl.2026.101989_b8","series-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill","year":"2020"},{"key":"10.1016\/j.csl.2026.101989_b9","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9726","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2019"},{"key":"10.1016\/j.csl.2026.101989_b10","doi-asserted-by":"crossref","DOI":"10.1145\/3366423.3380027","article-title":"Heterogeneous graph transformer","author":"Hu","year":"2020","journal-title":"Proc. the Web Conf. 2020"},{"key":"10.1016\/j.csl.2026.101989_b11","series-title":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7037","article-title":"MM-DFN: Multimodal dynamic fusion network for emotion recognition in conversations","author":"Hu","year":"2022"},{"key":"10.1016\/j.csl.2026.101989_b12","series-title":"MMGCN: Multimodal fusion via deep graph convolution network for emotion recognition in conversation","author":"Hu","year":"2021"},{"key":"10.1016\/j.csl.2026.101989_b13","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2016"},{"key":"10.1016\/j.csl.2026.101989_b14","series-title":"COGMEN: Contextualized GNN based multimodal emotion recognition","author":"Joshi","year":"2022"},{"key":"10.1016\/j.csl.2026.101989_b15","series-title":"Supervised contrastive learning","author":"Khosla","year":"2020"},{"key":"10.1016\/j.csl.2026.101989_b16","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.csl.2026.101989_b17","series-title":"Conference on Empirical Methods in Natural Language Processing","article-title":"Joyful: Joint modality fusion and graph contrastive learning for multimodal emotion recognition","author":"Li","year":"2023"},{"key":"10.1016\/j.csl.2026.101989_b18","series-title":"Roberta: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.csl.2026.101989_b19","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.csl.2026.101989_b20","series-title":"AAAI Conference on Artificial Intelligence","article-title":"Dialoguernn: An attentive RNN for emotion detection in conversations","author":"Majumder","year":"2018"},{"key":"10.1016\/j.csl.2026.101989_b21","doi-asserted-by":"crossref","first-page":"6472","DOI":"10.1109\/TAI.2024.3445325","article-title":"Deep imbalanced learning for multimodal emotion recognition in conversations","volume":"5","author":"Meng","year":"2023","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.csl.2026.101989_b22","series-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"10.1016\/j.csl.2026.101989_b23","series-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2018"},{"key":"10.1016\/j.csl.2026.101989_b24","doi-asserted-by":"crossref","first-page":"100943","DOI":"10.1109\/ACCESS.2019.2929050","article-title":"Emotion recognition in conversation: Research challenges, datasets, and recent advances","volume":"7","author":"Poria","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.csl.2026.101989_b25","series-title":"International Conference on Machine Learning","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.csl.2026.101989_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.aej.2025.11.020","article-title":"Emotion-aware cross-modal music generation based on multimodal emotion recognition","author":"Sun","year":"2025","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.csl.2026.101989_b27","series-title":"Neural Information Processing Systems","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.csl.2026.101989_b28","series-title":"Graph attention networks","author":"Velickovic","year":"2017"},{"key":"10.1016\/j.csl.2026.101989_b29","series-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","author":"Wang","year":"2020"},{"key":"10.1016\/j.csl.2026.101989_b30","doi-asserted-by":"crossref","DOI":"10.1145\/3308558.3313562","article-title":"Heterogeneous graph attention network","author":"Wang","year":"2019","journal-title":"World Wide Web Conf."},{"key":"10.1016\/j.csl.2026.101989_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128605","article-title":"Bimodal speech emotion recognition via contrastive self-alignment learning","volume":"293","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.csl.2026.101989_b32","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.csl.2026.101989_b33","series-title":"Do transformers really perform bad for graph representation?","author":"Ying","year":"2021"},{"key":"10.1016\/j.csl.2026.101989_b34","series-title":"Annual Meeting of the Association for Computational Linguistics","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"Zadeh","year":"2018"},{"key":"10.1016\/j.csl.2026.101989_b35","series-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000525?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000525?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T21:14:22Z","timestamp":1779225262000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230826000525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":35,"alternative-id":["S0885230826000525"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2026.101989","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GNN\u2013Transformer cross-view contrastive learning for multimodal conversational emotion recognition","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2026.101989","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":"101989"}}