{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:50:06Z","timestamp":1781585406382,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CCF-Baidu Open Fund","award":["No.OF2022025"],"award-info":[{"award-number":["No.OF2022025"]}]},{"name":"Open Research Projects of Zhejiang Lab","award":["No.2021KH0AB06"],"award-info":[{"award-number":["No.2021KH0AB06"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["(No.61831022, No.62276259, No.62201572, No.U21B2010)"],"award-info":[{"award-number":["(No.61831022, No.62276259, No.62201572, No.U21B2010)"]}]},{"name":"Beijing Municipal Science \\& Technology Commission, Administrative Commission of Zhongguancun Science Park","award":["No.Z211100004821013"],"award-info":[{"award-number":["No.Z211100004821013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612836","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T11:27:40Z","timestamp":1698406060000},"page":"9610-9614","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":62,"title":["MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5184-478X","authenticated-orcid":false,"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Licai","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Kang","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Mngyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Kexin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Yu","family":"He","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong Normal University, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Jinming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Ye","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Psychology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Psychology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Psychology, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3030-1280","authenticated-orcid":false,"given":"Erik","family":"Cambria","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3694-206X","authenticated-orcid":false,"given":"Guoying","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Imperial College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0477-587X","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"467","volume-title":"Proceedings of the International Conference on Multimodal Interaction","author":"Kahou Samira Ebrahimi","year":"2015","unstructured":"Samira Ebrahimi Kahou, Vincent Michalski, Kishore Konda, Roland Memisevic, and Christopher Pal. Recurrent neural networks for emotion recognition in video. In Proceedings of the International Conference on Multimodal Interaction, pages 467--474, 2015."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1034"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11041"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554810"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"e_1_3_2_1_12_1","volume-title":"Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. arXiv preprint arXiv:2208.07589","author":"Sun Licai","year":"2022","unstructured":"Licai Sun, Zheng Lian, Bin Liu, and Jianhua Tao. Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. arXiv preprint arXiv:2208.07589, 2022."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.50"},{"issue":"05","key":"e_1_3_2_1_14_1","first-page":"2402","article-title":"Deep partial multi-view learning","volume":"44","author":"Zhang Changqing","year":"2022","unstructured":"Changqing Zhang, Yajie Cui, Zongbo Han, Joey Tianyi Zhou, Huazhu Fu, and Qinghua Hu. Deep partial multi-view learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(05):2402--2415, 2022.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1582"},{"key":"e_1_3_2_1_17_1","article-title":"The biases of pre-trained language models: An empirical study on prompt-based sentiment analysis and emotion detection","author":"Mao Rui","year":"2022","unstructured":"Rui Mao, Qian Liu, Kai He, Wei Li, and Erik Cambria. The biases of pre-trained language models: An empirical study on prompt-based sentiment analysis and emotion detection. IEEE Transactions on Affective Computing, 2022.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In Proceedings of the Advances in Neural Information Processing Systems, 2022."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_53"},{"key":"e_1_3_2_1_22_1","first-page":"449","volume-title":"Proceedings of the International Conference on Multimodal Interaction","author":"Schuller Bj\u00f6rn","year":"2012","unstructured":"Bj\u00f6rn Schuller, Michel Valster, Florian Eyben, Roddy Cowie, and Maja Pantic. Avec 2012: the continuous audio\/visual emotion challenge. In Proceedings of the International Conference on Multimodal Interaction, pages 449--456. ACM, 2012."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661806.2661807"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806408"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133953"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531739"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666275"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2829994"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997638"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143004"},{"key":"e_1_3_2_1_35_1","first-page":"653","volume-title":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","author":"Dhall Abhinav","year":"2018","unstructured":"Abhinav Dhall, Amanjot Kaur, Roland Goecke, and Tom Gedeon. Emotiw 2018: Audio-video, student engagement and group-level affect prediction. In Proceedings of the 20th ACM International Conference on Multimodal Interaction, pages 653--656, 2018."},{"key":"e_1_3_2_1_36_1","first-page":"546","volume-title":"Proceedings of the International Conference on Multimodal Interaction","author":"Dhall Abhinav","year":"2019","unstructured":"Abhinav Dhall. Emotiw 2019: Automatic emotion, engagement and cohesion prediction tasks. In Proceedings of the International Conference on Multimodal Interaction, pages 546--550, 2019."},{"key":"e_1_3_2_1_37_1","first-page":"784","volume-title":"Proceedings of the International Conference on Multimodal Interaction","author":"Dhall Abhinav","year":"2020","unstructured":"Abhinav Dhall, Garima Sharma, Roland Goecke, and Tom Gedeon. Emotiw 2020: Driver gaze, group emotion, student engagement and physiological signal based challenges. In Proceedings of the International Conference on Multimodal Interaction, pages 784--789, 2020."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423673"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475957.3484450"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551792"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_2_1_42_1","volume-title":"Ctnet: Conversational transformer network for emotion recognition","author":"Lian Zheng","year":"2021","unstructured":"Zheng Lian, Bin Liu, and Jianhua Tao. Ctnet: Conversational transformer network for emotion recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29:985--1000, 2021."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.017"}],"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\/3581783.3612836","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:35Z","timestamp":1750178195000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612836"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":43,"alternative-id":["10.1145\/3581783.3612836","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612836","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"}}]}}