{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T13:25:48Z","timestamp":1783689948797,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441232, 62476068, 62306092, 62302474"],"award-info":[{"award-number":["62441232, 62476068, 62306092, 62302474"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3762088","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"14229-14235","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Combatting Data Imbalance and Noise in Micro-Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3249-0928","authenticated-orcid":false,"given":"Chuang","family":"Wang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, WeiHai, WeiHai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1259-7660","authenticated-orcid":false,"given":"Weidong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, HeFei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2083-2188","authenticated-orcid":false,"given":"Xu","family":"Cui","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, WeiHai, WeiHai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7840-736X","authenticated-orcid":false,"given":"Yiming","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9196-9818","authenticated-orcid":false,"given":"Zhaobo","family":"Qi","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, WeiHai, WeiHai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1047-3863","authenticated-orcid":false,"given":"Pengqi","family":"Huang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, WeiHai, WeiHai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2638-4324","authenticated-orcid":false,"given":"Xinyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, WeiHai, WeiHai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0042-7074","authenticated-orcid":false,"given":"Weigang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, WeiHai, WeiHai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_2_1","unstructured":"Mido Assran Adrien Bardes David Fan Quentin Garrido Russell Howes Matthew Muckley Ammar Rizvi Claire Roberts Koustuv Sinha Artem Zholus et al. 2025. V-jepa 2: Self-supervised video models enable understanding prediction and planning. arXiv preprint arXiv:2506.09985 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Revisiting Feature Prediction for Learning Visual Representations from Video. arXiv:2404.08471","author":"Bardes Adrien","year":"2024","unstructured":"Adrien Bardes, Quentin Garrido, Jean Ponce, Michael Rabbat, Yann LeCun, Mahmoud Assran, and Nicolas Ballas. 2024. Revisiting Feature Prediction for Learning Visual Representations from Video. arXiv:2404.08471 (2024)."},{"key":"e_1_3_2_1_4_1","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML, Vol. 2. 4.","journal-title":"ICML"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_6_1","volume-title":"Prototype learning for micro-gesture classification. arXiv preprint arXiv:2408.03097","author":"Chen Guoliang","year":"2024","unstructured":"Guoliang Chen, Fei Wang, Kun Li, Zhiliang Wu, Hehe Fan, Yi Yang, Meng Wang, and Dan Guo. 2024. Prototype learning for micro-gesture classification. arXiv preprint arXiv:2408.03097 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01761-6"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_2_1_9_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"e_1_3_2_1_14_1","volume-title":"MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion. arXiv preprint arXiv:2507.08344","author":"Gu Jihao","year":"2025","unstructured":"Jihao Gu, Fei Wang, Kun Li, Yanyan Wei, Zhiliang Wu, and Dan Guo. 2025. MM-Gesture: Towards Precise Micro-Gesture Recognition through Multimodal Fusion. arXiv preprint arXiv:2507.08344 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688973"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_18_1","volume-title":"3D convolutional neural networks for human action recognition","author":"Ji Shuiwang","year":"2012","unstructured":"Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 2012. 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, Vol. 35, 1 (2012), 221-231."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32509"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612856"},{"key":"e_1_3_2_1_22_1","volume-title":"Joint skeletal and semantic embedding loss for micro-gesture classification. arXiv preprint arXiv:2307.10624","author":"Li Kun","year":"2023","unstructured":"Kun Li, Dan Guo, Guoliang Chen, Xinge Peng, and Meng Wang. 2023b. Joint skeletal and semantic embedding loss for micro-gesture classification. arXiv preprint arXiv:2307.10624 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"MAC 2025: The 2nd Micro-Action Analysis Grand Challenge. In Proceedings of the 33rd ACM International Conference on Multimedia.","author":"Li Kun","year":"2025","unstructured":"Kun Li, Dan Guo, Xiaobai Li, Haoyu Chen, Pengyu Liu, Fei Wang, Jingjing Hu, Guoying Zhao, and Meng Wang. 2025b. MAC 2025: The 2nd Micro-Action Analysis Grand Challenge. In Proceedings of the 33rd ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_24_1","volume-title":"Mmad: Multi-label micro-action detection in videos. arXiv preprint arXiv:2407.05311","author":"Li Kun","year":"2024","unstructured":"Kun Li, Pengyu Liu, Dan Guo, Fei Wang, Zhiliang Wu, Hehe Fan, and Meng Wang. 2024. Mmad: Multi-label micro-action detection in videos. arXiv preprint arXiv:2407.05311 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"e_1_3_2_1_26_1","volume-title":"A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli. arXiv preprint arXiv:2503.15978","author":"Liu Pengyu","year":"2025","unstructured":"Pengyu Liu, Guohua Dong, Dan Guo, Kun Li, Fengling Li, Xun Yang, Meng Wang, and Xiaomin Ying. 2025a. A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli. arXiv preprint arXiv:2503.15978 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention. arXiv preprint arXiv:2507.09512","author":"Liu Pengyu","year":"2025","unstructured":"Pengyu Liu, Kun Li, Fei Wang, Yanyan Wei, Junhui She, and Dan Guo. 2025b. Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention. arXiv preprint arXiv:2507.09512 (2025)."},{"key":"e_1_3_2_1_28_1","volume-title":"Micro-gesture online recognition using learnable query points. arXiv preprint arXiv:2407.04490","author":"Liu Pengyu","year":"2024","unstructured":"Pengyu Liu, Fei Wang, Kun Li, Guoliang Chen, Yanyan Wei, Shengeng Tang, Zhiliang Wu, and Dan Guo. 2024. Micro-gesture online recognition using learnable query points. arXiv preprint arXiv:2407.04490 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones7030148"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3140465"},{"key":"e_1_3_2_1_33_1","volume-title":"Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_34_1","volume-title":"Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524","author":"Tian Yunjie","year":"2025","unstructured":"Yunjie Tian, Qixiang Ye, and David Doermann. 2025. Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in neural information processing systems","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. 2022. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in neural information processing systems, Vol. 35 (2022), 10078-10093."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"e_1_3_2_1_40_1","volume-title":"Towards good practices for very deep two-stream convnets. arXiv preprint arXiv:1507.02159","author":"Wang Limin","year":"2015","unstructured":"Limin Wang, Yuanjun Xiong, Zhe Wang, and Yu Qiao. 2015b. Towards good practices for very deep two-stream convnets. arXiv preprint arXiv:1507.02159 (2015)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_42_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3762088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:40:05Z","timestamp":1765309205000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3762088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":44,"alternative-id":["10.1145\/3746027.3762088","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3762088","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}