{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:01:35Z","timestamp":1777568495615,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"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":"National Key R&D Program of China","award":["2021YFC3310100"],"award-info":[{"award-number":["2021YFC3310100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176251, 61976219"],"award-info":[{"award-number":["62176251, 61976219"]}],"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612496","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"2723-2733","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Data-Efficient Masked Video Modeling for Self-supervised Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5121-1682","authenticated-orcid":false,"given":"Qiankun","family":"Li","sequence":"first","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5502-2535","authenticated-orcid":false,"given":"Xiaolong","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2742-3613","authenticated-orcid":false,"given":"Zhifan","family":"Wan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8788-5811","authenticated-orcid":false,"given":"Lanqing","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4455-4123","authenticated-orcid":false,"given":"Shuzhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Huawei Cloud Computing Technologies Co., Ltd, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8899-3996","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-392X","authenticated-orcid":false,"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1859-900X","authenticated-orcid":false,"given":"Zengfu","family":"Wang","sequence":"additional","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences & University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume":"33","author":"Alayrac Jean-Baptiste","year":"2020","unstructured":"Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, Relja Arandjelovi\u0107, Jason Ramapuram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, and Andrew Zisserman. 2020. Self-supervised multimodal versatile networks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 25--37.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_4_1","volume-title":"BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/212094.212141"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00911"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_13_1","volume-title":"BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548546"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_1_16_1","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume":"35","author":"Feichtenhofer Christoph","year":"2022","unstructured":"Christoph Feichtenhofer, Yanghao Li, Kaiming He, et al. 2022. Masked autoencoders as spatiotemporal learners. Advances in Neural Information Processing Systems, Vol. 35 (2022), 35946--35958.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"e_1_3_2_1_18_1","volume-title":"Armand Joulin, and Ishan Misra.","author":"Girdhar Rohit","year":"2022","unstructured":"Rohit Girdhar, Alaaeldin El-Nouby, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, and Ishan Misra. 2022. OmniMAE: Single model masked pretraining on images and videos. arXiv preprint arXiv:2206.08356 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"e_1_3_2_1_20_1","volume-title":"Theory, Applications and Future Trends. arXiv preprint arXiv:2301.05712","author":"Gui Jie","year":"2023","unstructured":"Jie Gui, Tuo Chen, Qiong Cao, Zhenan Sun, Hao Luo, and Dacheng Tao. 2023. A Survey of Self-Supervised Learning from Multiple Perspectives: Algorithms, Theory, Applications and Future Trends. arXiv preprint arXiv:2301.05712 (2023)."},{"key":"e_1_3_2_1_21_1","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume":"33","author":"Han Tengda","year":"2020","unstructured":"Tengda Han, Weidi Xie, and Andrew Zisserman. 2020. Self-supervised co-training for video representation learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 5679--5690.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_23_1","first-page":"279","article-title":"Tracking facial feature points using kanade-lucas-tomasi approach","volume":"16","author":"Hong Duan","year":"2004","unstructured":"Duan Hong. 2004. Tracking facial feature points using kanade-lucas-tomasi approach. Journal of Computer Aided Design and Computer Graphics, Vol. 16, 3 (2004), 279--283.","journal-title":"Journal of Computer Aided Design and Computer Graphics"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01367"},{"key":"e_1_3_2_1_25_1","volume-title":"Runner-Up Solution to Google Universal Image Embedding Competition","author":"Huang Xiaolong","year":"2022","unstructured":"Xiaolong Huang and QianKun Li. 2022. Runner-Up Solution to Google Universal Image Embedding Competition 2022. arXiv preprint arXiv:2210.08735 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Yuqi Huo Mingyu Ding Haoyu Lu Zhiwu Lu Tao Xiang Ji-Rong Wen Ziyuan Huang Jianwen Jiang Shiwei Zhang Mingqian Tang et al. 2021. Self-supervised video representation learning with constrained spatiotemporal jigsaw. (2021).","DOI":"10.24963\/ijcai.2021\/104"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_29_1","volume-title":"Efficient self-supervised vision transformers for representation learning. arXiv preprint arXiv:2106.09785","author":"Li Chunyuan","year":"2021","unstructured":"Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Mei Gao, Bin Xiao, Xiyang Dai, Lu Yuan, and Jianfeng Gao. 2021. Efficient self-supervised vision transformers for representation learning. arXiv preprint arXiv:2106.09785 (2021)."},{"key":"e_1_3_2_1_30_1","volume-title":"RoBERTa: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","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. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548238"},{"key":"e_1_3_2_1_36_1","volume-title":"Tel Aviv","author":"Ni Jingcheng","year":"2022","unstructured":"Jingcheng Ni, Nan Zhou, Jie Qin, Qian Wu, Junqi Liu, Boxun Li, and Di Huang. 2022b. Motion Sensitive Contrastive Learning for Self-supervised Video Representation. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXV. Springer, 457--474."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7990--8001","author":"Ding Shuangrui","year":"2021","unstructured":"Rui Qian, Yuxi Li, Huabin Liu, John See, Shuangrui Ding, Xian Liu, Dian Li, and Weiyao Lin. 2021. Enhancing self-supervised video representation learning via multi-level feature optimization. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7990--8001."},{"key":"e_1_3_2_1_38_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551791"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00387"},{"key":"e_1_3_2_1_41_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00092"},{"key":"e_1_3_2_1_43_1","volume-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv preprint arXiv:2203.12602","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. arXiv preprint arXiv:2203.12602 (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01446-y"},{"key":"e_1_3_2_1_51_1","volume-title":"VideoGPT: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157","author":"Yan Wilson","year":"2021","unstructured":"Wilson Yan, Yunzhi Zhang, Pieter Abbeel, and Aravind Srinivas. 2021. VideoGPT: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157 (2021)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3556644"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351040"}],"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\/3581783.3612496","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:05Z","timestamp":1755820925000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":55,"alternative-id":["10.1145\/3581783.3612496","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612496","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"}}]}}