{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T09:37:36Z","timestamp":1780047456501,"version":"3.53.1"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2053"],"award-info":[{"award-number":["U22B2053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017489","name":"Alibaba DAMO Academy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3263288","type":"journal-article","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T17:33:29Z","timestamp":1680197609000},"page":"218-233","source":"Crossref","is-referenced-by-count":52,"title":["MAR: <u>M<\/u>asked Autoencoders for Efficient <u>A<\/u>ction <u>R<\/u>ecognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4776-357X","authenticated-orcid":false,"given":"Zhiwu","family":"Qing","sequence":"first","affiliation":[{"name":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6929-5295","authenticated-orcid":false,"given":"Shiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4544-0427","authenticated-orcid":false,"given":"Ziyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Advanced Robotics Centre, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0785-3367","authenticated-orcid":false,"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7046-7587","authenticated-orcid":false,"given":"Yuehuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiliang","family":"Lv","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2736-3920","authenticated-orcid":false,"given":"Changxin","family":"Gao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9167-1496","authenticated-orcid":false,"given":"Nong","family":"Sang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref7","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref9","first-page":"7780","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref15","article-title":"LiteEval: A coarse-to-fine framework for resource efficient video recognition","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wu","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00609"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref18","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Feichtenhofer","year":"2022"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref21","article-title":"A closer look at self-supervised lightweight vision transformers","author":"Wang","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref32","article-title":"TAda! temporally-adaptive convolutions for video understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3148588"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref45","article-title":"LongFormer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref48","article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007826"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/98"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00346"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref54","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc.","author":"Devlin","year":"2019"},{"key":"ref55","first-page":"642","article-title":"UnilmV2: Pseudo-masked language models for unified language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao","year":"2020"},{"key":"ref56","article-title":"Roberta: A. robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref57","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019"},{"key":"ref58","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Dong","year":"2019"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref62","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord","year":"2017"},{"key":"ref63","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref64","article-title":"BEIT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref68","article-title":"VIMPAC: Video pre-training via masked token prediction and contrastive learning","author":"Tan","year":"2021"},{"key":"ref69","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Kornblith","year":"2019"},{"key":"ref70","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref71","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref73","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"issue":"1","key":"ref77","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref78","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref81","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref85","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Patrick","year":"2021"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_28"},{"key":"ref88","article-title":"Can an image classifier suffice for action recognition?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fan","year":"2022"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3189253"},{"key":"ref90","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Han","year":"2020"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00153"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00133"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3244126"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00784"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01345"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10089159.pdf?arnumber=10089159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:58:01Z","timestamp":1725904681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3263288","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}