{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:45:47Z","timestamp":1774539947599,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["U20A20183"],"award-info":[{"award-number":["U20A20183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62021001"],"award-info":[{"award-number":["62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association, Chinese Academy of Sciences","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Graphics Processing Unit (GPU) Cluster Built by Multimedia Computing and Communication (MCC) Laboratory of Information Science and Technology Institution, University of Science and Technology of China"},{"DOI":"10.13039\/501100001809","name":"Supercomputing Center, USTC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3409728","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T18:06:08Z","timestamp":1717610768000},"page":"10793-10804","source":"Crossref","is-referenced-by-count":18,"title":["MASA: Motion-Aware Masked Autoencoder With Semantic Alignment for Sign Language Recognition"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7098-1690","authenticated-orcid":false,"given":"Weichao","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geospatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0327-1562","authenticated-orcid":false,"given":"Hezhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Visual Informatics Group, University of Texas at Austin, Austin, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geospatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-9086","authenticated-orcid":false,"given":"Yunyao","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geospatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3048-6980","authenticated-orcid":false,"given":"Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei Comprehensive National Science Center, Institute of Artificial Intelligence, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, CAS Key Laboratory of Technology in Geospatial Information Processing and Application System, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3070438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3143074"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref8","volume-title":"OpenMMLab Pose Estimation Toolbox and Benchmark","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383346"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/AMFG.2003.1240841"},{"key":"ref13","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gidaris"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.831970"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3268368"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269220"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16247"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3436754"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00249"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00378"},{"key":"ref26","first-page":"1","article-title":"MS-ASL: A large-scale data set and benchmark for understanding American sign language","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Joze"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10582029"},{"key":"ref28","article-title":"Quantitative survey of the state of the art in sign language recognition","author":"Koller","year":"2020","journal-title":"arXiv:2008.09918"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1121-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00033"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01896"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00624"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561120"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref38","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01169"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00975"},{"key":"ref43","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113794"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00345"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.150"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3028072"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3151362"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/iscv.1995.477012"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2735952"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref57","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tong"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW52041.2021.00008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2915032"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2298382"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2999384"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109665"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296668"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25470"},{"key":"ref70","first-page":"1","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref71","article-title":"MotionBERT: Unified pretraining for human motion analysis","author":"Zhu","year":"2022","journal-title":"arXiv:2210.06551"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01430"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768433\/10549522.pdf?arnumber=10549522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:48:58Z","timestamp":1732736938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10549522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":72,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3409728","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}