{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:17:28Z","timestamp":1782965848289,"version":"3.54.5"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"funder":[{"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":[[2024,12]]},"DOI":"10.1016\/j.inffus.2024.102590","type":"journal-article","created":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T16:39:19Z","timestamp":1721493559000},"page":"102590","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":37,"special_numbering":"C","title":["Adversarial alignment and graph fusion via information bottleneck for multimodal emotion recognition in conversations"],"prefix":"10.1016","volume":"112","author":[{"given":"Yuntao","family":"Shou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-9787-2002","authenticated-orcid":false,"given":"Tao","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuchen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"9","key":"10.1016\/j.inffus.2024.102590_b1","doi-asserted-by":"crossref","first-page":"4332","DOI":"10.1109\/TNNLS.2021.3056664","article-title":"Attention-emotion-enhanced convolutional LSTM for sentiment analysis","volume":"33","author":"Huang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"7","key":"10.1016\/j.inffus.2024.102590_b2","doi-asserted-by":"crossref","first-page":"2901","DOI":"10.1109\/TNNLS.2020.3008938","article-title":"Time\u2013frequency representation and convolutional neural network-based emotion recognition","volume":"32","author":"Khare","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2024.102590_b3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2022.3188547","article-title":"Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrieval","author":"Qian","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2024.102590_b4","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.inffus.2019.02.007","article-title":"Affective video content analysis based on multimodal data fusion in heterogeneous networks","volume":"51","author":"Guo","year":"2019","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2024.102590_b5","series-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI","first-page":"4524","article-title":"Cauain: Causal aware interaction network for emotion recognition in conversations","author":"Zhao","year":"2022"},{"key":"10.1016\/j.inffus.2024.102590_b6","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.inffus.2024.102590_b7","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.inffus.2024.102590_b8","doi-asserted-by":"crossref","unstructured":"J. Hu, Y. Liu, J. Zhao, Q. Jin, MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation, in: 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), 2021, pp. 5666\u20135675.","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"10.1016\/j.inffus.2024.102590_b9","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/j.ins.2022.11.076","article-title":"Multi-modal fusion network with complementarity and importance for emotion recognition","volume":"619","author":"Liu","year":"2023","journal-title":"Inform. Sci."},{"key":"10.1016\/j.inffus.2024.102590_b10","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.inffus.2024.102590_b11","doi-asserted-by":"crossref","unstructured":"N. Majumder, S. Poria, D. Hazarika, R. Mihalcea, A. Gelbukh, E. Cambria, Dialoguernn: An attentive rnn for emotion detection in conversations, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, (01) 2019, pp. 6818\u20136825.","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"10.1016\/j.inffus.2024.102590_b12","doi-asserted-by":"crossref","unstructured":"F. Eyben, M. W\u00f6llmer, B. Schuller, Opensmile: the munich versatile and fast open-source audio feature extractor, in: Proceedings of the 18th ACM International Conference on Multimedia, 2010, pp. 1459\u20131462.","DOI":"10.1145\/1873951.1874246"},{"key":"10.1016\/j.inffus.2024.102590_b13","first-page":"1","article-title":"PIRNet: Personality-enhanced iterative refinement network for emotion recognition in conversation","author":"Lian","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2024.102590_b14","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.2024.102590_b15","series-title":"Proceedings of the 22nd Conference on Computational Natural Language Learning","first-page":"251","article-title":"Multi-modal sequence fusion via recursive attention for emotion recognition","author":"Beard","year":"2018"},{"key":"10.1016\/j.inffus.2024.102590_b16","first-page":"1","article-title":"LR-GCN: Latent relation-aware graph convolutional network for conversational emotion recognition","author":"Ren","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2024.102590_b17","doi-asserted-by":"crossref","first-page":"3793","DOI":"10.1109\/TMM.2020.3032037","article-title":"C-GCN: correlation based graph convolutional network for audio-video emotion recognition","volume":"23","author":"Nie","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2024.102590_b18","first-page":"1","article-title":"Hierarchical context-based emotion recognition with scene graphs","author":"Wu","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2024.102590_b19","first-page":"1","article-title":"Learning enhanced acoustic latent representation for small scale affective corpus with adversarial cross corpora integration","author":"Chang","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2024.102590_b20","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6329","article-title":"Contrastive unsupervised learning for speech emotion recognition","author":"Li","year":"2021"},{"key":"10.1016\/j.inffus.2024.102590_b21","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5948","article-title":"Contrastive adversarial learning for person independent facial emotion recognition","volume":"Vol. 35","author":"Kim","year":"2021"},{"key":"10.1016\/j.inffus.2024.102590_b22","first-page":"1","article-title":"A self-fusion network based on contrastive learning for group emotion recognition","author":"Wang","year":"2022","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.inffus.2024.102590_b23","first-page":"1","article-title":"Emoberta: Speaker-aware emotion recognition in conversation with Roberta","volume":"2021","author":"Kim","year":"2021","journal-title":"Comput. Res. Repos.-arXiv"},{"key":"10.1016\/j.inffus.2024.102590_b24","doi-asserted-by":"crossref","unstructured":"V. Chudasama, P. Kar, A. Gudmalwar, N. Shah, P. Wasnik, N. Onoe, M2fnet: Multi-modal fusion network for emotion recognition in conversation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4652\u20134661.","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"10.1016\/j.inffus.2024.102590_b25","doi-asserted-by":"crossref","unstructured":"W. Shen, S. Wu, Y. Yang, X. Quan, Directed Acyclic Graph Network for Conversational Emotion Recognition, in: 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), 2021, pp. 1551\u20131560.","DOI":"10.18653\/v1\/2021.acl-long.123"},{"key":"10.1016\/j.inffus.2024.102590_b26","series-title":"Findings of the Association for Computational Linguistics: ACL 2022","first-page":"1610","article-title":"EmoCaps: Emotion capsule based model for conversational emotion recognition","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2024.102590_b27","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","first-page":"154","article-title":"DialogueGCN: A graph convolutional neural network for emotion recognition in conversation","author":"Ghosal","year":"2019"},{"key":"10.1016\/j.inffus.2024.102590_b28","unstructured":"A.A. Alemi, I. Fischer, J.V. Dillon, K. Murphy, Deep Variational Information Bottleneck, in: International Conference on Learning Representations, 2016."},{"key":"10.1016\/j.inffus.2024.102590_b29","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"527","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2019"},{"issue":"4","key":"10.1016\/j.inffus.2024.102590_b30","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.inffus.2024.102590_b31","unstructured":"D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization, in: International Conference on Learning Representations, 2015."},{"key":"10.1016\/j.inffus.2024.102590_b32","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"key":"10.1016\/j.inffus.2024.102590_b33","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."},{"key":"10.1016\/j.inffus.2024.102590_b34","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.inffus.2024.102590_b35","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.inffus.2024.102590_b36","doi-asserted-by":"crossref","unstructured":"S. Mai, H. Hu, S. Xing, Modality to modality translation: An adversarial representation learning and graph fusion network for multimodal fusion, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, (01) 2020, pp. 164\u2013172.","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"10.1016\/j.inffus.2024.102590_b37","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3234553","article-title":"Gcnet: Graph completion network for incomplete multimodal learning in conversation","author":"Lian","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2024.102590_b38","doi-asserted-by":"crossref","unstructured":"M.K. Hasan, W. Rahman, A.B. Zadeh, J. Zhong, M.I. Tanveer, L.-P. Morency, M.E. Hoque, UR-FUNNY: A Multimodal Language Dataset for Understanding Humor, in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP, 2019, pp. 2046\u20132056.","DOI":"10.18653\/v1\/D19-1211"},{"key":"10.1016\/j.inffus.2024.102590_b39","unstructured":"P. Veli\u010dkovi\u0107, W. Fedus, W.L. Hamilton, P. Li\u00f2, Y. Bengio, R.D. Hjelm, Deep Graph Infomax, in: International Conference on Learning Representations, 2018."},{"key":"10.1016\/j.inffus.2024.102590_b40","unstructured":"F.-Y. Sun, J. Hoffman, V. Verma, J. Tang, InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization, in: International Conference on Learning Representations, 2019."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S1566253524003683?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S1566253524003683?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T22:32:37Z","timestamp":1728513157000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253524003683"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":40,"alternative-id":["S1566253524003683"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.inffus.2024.102590","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adversarial alignment and graph fusion via information bottleneck for multimodal emotion recognition in conversations","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.inffus.2024.102590","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 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":"102590"}}