{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T02:38:45Z","timestamp":1783564725105,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100003303","name":"Research Foundation of Ministry of Education of China","doi-asserted-by":"publisher","award":["18JZD015"],"award-info":[{"award-number":["18JZD015"]}],"id":[{"id":"10.13039\/100003303","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB3103602, 2017YFC1200500"],"award-info":[{"award-number":["2022YFB3103602, 2017YFC1200500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176187"],"award-info":[{"award-number":["62176187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000885","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000885","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"NExT Research Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612053","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"5923-5934","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":59,"title":["Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-5540","authenticated-orcid":false,"given":"Bobo","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"NExT Research Center, School of Computing, National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9973-3305","authenticated-orcid":false,"given":"Lizi","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8714-4151","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6543-2548","authenticated-orcid":false,"given":"Chong","family":"Teng","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1816-1761","authenticated-orcid":false,"given":"Donghong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9613-5927","authenticated-orcid":false,"given":"Fei","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1034"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18--1208"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_3_2_1_4_1","volume-title":"Workshop on COLING. International Conference on Computational Linguistics, Virtual, 44--56","author":"Bansal Keshav","year":"2022","unstructured":"Keshav Bansal, Harsh Agarwal, Abhinav Joshi, and Ashutosh Modi. 2022. Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shifts. In Workshop on COLING. International Conference on Computational Linguistics, Virtual, 44--56. https:\/\/aclanthology.org\/2022.mmmpie-1.6"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1566"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of Workshop Affective Content Analysis with AAAI (CEUR Workshop Proceedings","volume":"99","author":"Chen Feiyang","year":"2020","unstructured":"Feiyang Chen, Ziqian Luo, Yanyan Xu, and Dengfeng Ke. 2020. Complementary Fusion of Multi-Features and Multi-Modalities in Sentiment Analysis. In Proceedings of Workshop Affective Content Analysis with AAAI (CEUR Workshop Proceedings, Vol. 2614). CEUR-WS.org, New York, USA, 82--99. https:\/\/ceur-ws.org\/Vol-2614\/AffCon20_session1_complementary.pdf"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475661"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of NeurIPS. IEEE","author":"Charles Corbi\u00e8","year":"2019","unstructured":"Charles Corbi\u00e8 re, Nicolas Thome, Avner Bar-Hen, Matthieu Cord, and Patrick P\u00e9rez. 2019. Addressing Failure Prediction by Learning Model Confidence. In Proceedings of NeurIPS. IEEE, Vancouver, BC, Canada, 2898--2909. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/757f843a169cc678064d9530d12a1881-Abstract.html"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586075"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.70"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1382"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02005"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"e_1_3_2_1_23_1","volume-title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","author":"Hu Guimin","year":"2022","unstructured":"Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, and Yongbin Li. 2022b. UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition. In Proceedings of EMNLP. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 7837--7851. https:\/\/aclanthology.org\/2022.emnlp-main.534"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3205919"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479939"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.597"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545572"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.36"},{"key":"e_1_3_2_1_32_1","volume-title":"Narayanan","author":"Lee Chi-Chun","year":"2009","unstructured":"Chi-Chun Lee, Carlos Busso, Sungbok Lee, and Shrikanth S. Narayanan. 2009. Modeling mutual influence of interlocutor emotion states in dyadic spoken interactions. In INTERSPEECH. ISCA, Brighton, United Kingdom, 1983--1986. http:\/\/www.isca-speech.org\/archive\/interspeech_2009\/i09_1983.html"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.416"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.370"},{"key":"e_1_3_2_1_35_1","volume-title":"A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation. CoRR","author":"Li Jiangnan","year":"2020","unstructured":"Jiangnan Li, Zheng Lin, Peng Fu, Qingyi Si, and Weiping Wang. 2020b. A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation. CoRR, Vol. abs\/2012.14781 (2020). [arXiv]2012.14781 https:\/\/arxiv.org\/abs\/2012.14781"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"e_1_3_2_1_37_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR, Vol. abs\/1907.11692 (2019). showeprint[arXiv]1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of ICLR. OpenReview.net","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of ICLR. OpenReview.net, New Orleans, LA. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_39_1","volume-title":"Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion","author":"Mai Sijie","unstructured":"Sijie Mai, Haifeng Hu, and Songlong Xing. 2020. Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion. In Proceedings of AAAI. AAAI Press, New York, USA, 164--172. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/5347"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2349"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.229"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.09172"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531912"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.01.011"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.8"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746464"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19--1656"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3223517"},{"key":"e_1_3_2_1_54_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey E. Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.96"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.34"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"e_1_3_2_1_59_1","volume-title":"Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis","author":"Yu Wenmeng","unstructured":"Wenmeng Yu, Hua Xu, Ziqi Yuan, and Jiele Wu. 2021. Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis. In Proceedings of AAAI. AAAI Press, Virtual Event, 10790--10797. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17289"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1115"},{"key":"e_1_3_2_1_61_1","volume-title":"Navonil Mazumder, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency.","author":"Zadeh Amir","year":"2018","unstructured":"Amir Zadeh, Paul Pu Liang, Navonil Mazumder, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2018. Memory Fusion Network for Multi-view Sequential Learning. In Proceedings of AAAI. AAAI Press, New Orleans, Louisiana, USA, 5634--5641. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17341"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2973828"},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of COLING. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 7020--7030","author":"Zhao Weixiang","year":"2022","unstructured":"Weixiang Zhao, Yanyan Zhao, and Bing Qin. 2022. MuCDN: Mutual Conversational Detachment Network for Emotion Recognition in Multi-Party Conversations. In Proceedings of COLING. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 7020--7030. https:\/\/aclanthology.org\/2022.coling-1.612"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.125"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612053","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:18Z","timestamp":1755820938000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":64,"alternative-id":["10.1145\/3581783.3612053","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612053","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}