{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:21:30Z","timestamp":1780579290994,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":19,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176165"],"award-info":[{"award-number":["62176165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Stable Support Projects for Shenzhen Higher Education Institutions","award":["SZWD2021011"],"award-info":[{"award-number":["SZWD2021011"]}]},{"name":"Natural Science Foundation of Top Talent of SZTU","award":["GDRC202131"],"award-info":[{"award-number":["GDRC202131"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612840","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"9436-9440","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Semi-Supervised Multimodal Emotion Recognition with Expression MAE"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2854-7425","authenticated-orcid":false,"given":"Zebang","family":"Cheng","sequence":"first","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7835-9352","authenticated-orcid":false,"given":"Yuxiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4836-0091","authenticated-orcid":false,"given":"Zhaoru","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1049-4399","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4338-687X","authenticated-orcid":false,"given":"Shuyi","family":"Mao","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5250-7258","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4965-4670","authenticated-orcid":false,"given":"Daijun","family":"Ding","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3581-9476","authenticated-orcid":false,"given":"Bowen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5783-321X","authenticated-orcid":false,"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, 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":"10.38094\/jastt20291"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1037\/a0017088"},{"key":"e_1_3_2_1_4_1","volume-title":"Revisiting pre-trained models for Chinese natural language processing. arXiv preprint arXiv:2004.13922","author":"Cui Yiming","year":"2020","unstructured":"Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, and Guoping Hu. 2020. Revisiting pre-trained models for Chinese natural language processing. arXiv preprint arXiv:2004.13922 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110025"},{"key":"e_1_3_2_1_6_1","volume-title":"Masked autoencoders are scalable vision learners","author":"He Kaiming","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross Girshick. [n.,d.]. Masked autoencoders are scalable vision learners. IEEE. 15979--15988 pages."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.102423"},{"key":"e_1_3_2_1_9_1","volume-title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning. arXiv preprint arXiv:2304","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Haiyang Sun, Licai Sun, Jinming Zhao, Ye Liu, Bin Liu, Jiangyan Yi, Meng Wang, Erik Cambria, Guoying Zhao, et al. 2023. MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning. arXiv preprint arXiv:2304.08981 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.07.046"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICETET.2010.85"},{"key":"e_1_3_2_1_13_1","volume-title":"Multimodal emotion recognition in response to videos","author":"Soleymani Mohammad","year":"2011","unstructured":"Mohammad Soleymani, Maja Pantic, and Thierry Pun. 2011. Multimodal emotion recognition in response to videos. IEEE transactions on affective computing, Vol. 3, 2 (2011), 211--223."},{"key":"e_1_3_2_1_14_1","unstructured":"Zhan Tong Yibing Song Jue Wang and Limin Wang. [n. d.]. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"e_1_3_2_1_16_1","volume-title":"Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135","author":"Wang Yuxuan","year":"2017","unstructured":"Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, et al. 2017. Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"e_1_3_2_1_18_1","volume-title":"Learning deep global multiscale and local attention features for facial expression recognition in the wild","author":"Zhao Zengqun","unstructured":"Zengqun Zhao, Qingshan Liu, and Shanmin Wang. [n.,d.]. Learning deep global multiscale and local attention features for facial expression recognition in the wild. IEEE Transactions on Image Processing, Vol. 30 ( [n.,d.]), 6544--6556,."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355713"}],"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\/3581783.3612840","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:00Z","timestamp":1755821520000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":19,"alternative-id":["10.1145\/3581783.3612840","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612840","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"}}]}}