{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:22:25Z","timestamp":1791303745274,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":40,"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":[{"name":"Key R&D Program of Shandong (Major scientific and technological innovation projects)","award":["No.:2022CXGC020107"],"award-info":[{"award-number":["No.:2022CXGC020107"]}]},{"name":"Special Fund for Distinguished Professors of Shandong Jianzhu University"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.:62006142, No.:U1936203, and No.:62236003"],"award-info":[{"award-number":["No.:62006142, No.:U1936203, and No.:62236003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen College Stability Support Plan","award":["No.:GXWD20220817144428005"],"award-info":[{"award-number":["No.:GXWD20220817144428005"]}]},{"name":"National Natural Science Foundation (NSF) of China","award":["No.:62276155"],"award-info":[{"award-number":["No.:62276155"]}]},{"name":"NSF of Shandong Province","award":["No.:ZR2021MF040"],"award-info":[{"award-number":["No.:ZR2021MF040"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613846","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"5947-5955","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Unlocking the Power of Multimodal Learning for Emotion Recognition in Conversation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1897-6557","authenticated-orcid":false,"given":"Yunxiao","family":"Wang","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5764","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4370-6616","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-8286","authenticated-orcid":false,"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6901-5476","authenticated-orcid":false,"given":"Xin","family":"Luo","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics.","author":"Blitzer John","year":"2007","unstructured":"John Blitzer, Mark Dredze, and Fernando Pereira. 2007. Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification. In Proceedings of the Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591673"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing. 154--164","author":"Ghosal Deepanway","unstructured":"Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya, and Alexander F. Gelbukh. 2019. DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing. 154--164."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1280"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1193"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation.","author":"Hsu Chao-Chun","year":"2018","unstructured":"Chao-Chun Hsu, Sheng-Yeh Chen, Chuan-Chun Kuo, Ting-Hao K. Huang, and Lun-Wei Ku. 2018. EmotionLines: An Emotion Corpus of Multi-Party Conversations. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceeding of the Annual Conference on Neural Information Processing Systems. 10944--10956","author":"Huang Yu","year":"2021","unstructured":"Yu Huang, Chenzhuang Du, Zihui Xue, Xuanyao Chen, Hang Zhao, and Longbo Huang. 2021. What Makes Multi-Modal Learning Better than Single (Provably). In Proceeding of the Annual Conference on Neural Information Processing Systems. 10944--10956."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.597"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the ACM International Conference on Multimedia. 3370--3379","author":"Lao Mingrui","unstructured":"Mingrui Lao, Yanming Guo, Yu Liu, Wei Chen, Nan Pu, and Michael S. Lew. 2021. From Superficial to Deep: Language Bias driven Curriculum Learning for Visual Question Answering. In Proceedings of the ACM International Conference on Multimedia. 3370--3379."},{"key":"e_1_3_2_2_17_1","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing. 986--995","author":"Li Yanran","year":"2017","unstructured":"Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. In Proceedings of the Eighth International Joint Conference on Natural Language Processing. 986--995."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286259"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceeding of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing. 148--157","author":"Liang Chen","year":"2022","unstructured":"Chen Liang, Chong Yang, Jing Xu, Juyang Huang, Yongliang Wang, and Yang Dong. 2022. SPAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation. In Proceeding of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing. 148--157."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217449"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2875363"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Navonil Majumder Soujanya Poria Devamanyu Hazarika Rada Mihalcea Alexander Gelbukh and E. Cambria. 2019. DialogueRNN: An Attentive RNN for Emotion Detection in Conversations. In Proceeding of the Association for the Advancement of Artificial Intelligence. 6818--6825.","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_2_23_1","volume-title":"Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1275--1284","author":"Melville Prem","unstructured":"Prem Melville, Wojciech Gryc, and Richard D. Lawrence. 2009. Sentiment analysis of blogs by combining lexical knowledge with text classification. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1275--1284."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548180"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_2_26_1","volume-title":"Winter Conference on Applications of Computer Vision","author":"Planamente Mirco","year":"2021","unstructured":"Mirco Planamente, Chiara Plizzari, Emanuele Alberti, and Barbara Caputo. 2021. Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition. Winter Conference on Applications of Computer Vision (2021), 163--174."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929050"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS.2017.7945451"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.102447"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3270940"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3101421"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923608"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceeding of the International Conference on Machine Learning. 24043--24055","author":"Wu Nan","unstructured":"Nan Wu, Stanis\u0140aw Jastrzebski, Kyunghyun Cho, and Krzysztof J. Geras. 2022. Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks. In Proceeding of the International Conference on Machine Learning. 24043--24055."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096655"},{"key":"e_1_3_2_2_38_1","volume-title":"Choi","author":"Zahiri Sayyed M.","year":"2018","unstructured":"Sayyed M. Zahiri and Jinho D. Choi. 2018. Emotion Detection on TV Show Transcripts with Sequence-Based Convolutional Neural Networks. In Proceeding of the Association for the Advancement of Artificial Intelligence, Vol. WS-19. 44--52."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413949"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/628"}],"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\/3581783.3613846","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:53:49Z","timestamp":1755820429000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613846"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":40,"alternative-id":["10.1145\/3581783.3613846","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613846","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"}}]}}