{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T05:54:11Z","timestamp":1771566851185,"version":"3.50.1"},"reference-count":76,"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":["62222207"],"award-info":[{"award-number":["62222207"]}],"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":["62072245"],"award-info":[{"award-number":["62072245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20211520"],"award-info":[{"award-number":["BK20211520"]}],"id":[{"id":"10.13039\/501100004608","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.2024.3416732","type":"journal-article","created":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T17:41:44Z","timestamp":1718818904000},"page":"10718-10731","source":"Crossref","is-referenced-by-count":15,"title":["Motion-Aware Mask Feature Reconstruction for Skeleton-Based Action Recognition"],"prefix":"10.1109","volume":"34","author":[{"given":"Xingyu","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2823910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3179243"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2868123"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref13","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref14","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25495"},{"key":"ref19","article-title":"SkeletonMAE: Spatial\u2013temporal masked autoencoders for self-supervised skeleton action recognition","author":"Wu","year":"2022","journal-title":"arXiv:2209.02399"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611774"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref26","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02232"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref29","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_20"},{"key":"ref31","article-title":"MILAN: Masked image pretraining on language assisted representation","author":"Hou","year":"2022","journal-title":"arXiv:2208.06049"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611888"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.198"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.772"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.76"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967191"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428459"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3240472"},{"key":"ref45","article-title":"Hypergraph transformer for skeleton-based action recognition","author":"Zhou","year":"2022","journal-title":"arXiv:2211.09590"},{"key":"ref46","article-title":"STEP CATFormer: Spatial\u2013temporal effective body-part cross attention transformer for skeleton-based action recognition","author":"Huu Bao Long","year":"2023","journal-title":"arXiv:2312.03288"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3207577"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref49","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv:2111.07783"},{"key":"ref50","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/184"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201518"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3129616"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475307"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01807"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3194350"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"ref71","article-title":"Contrastive learning from spatio-temporal mixed skeleton sequences for self-supervised skeleton-based action recognition","author":"Chen","year":"2022","journal-title":"arXiv:2207.03065"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/95"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref74","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"26","author":"Frome"},{"key":"ref75","article-title":"Skeleton based zero shot action recognition in joint pose-language semantic space","author":"Jasani","year":"2019","journal-title":"arXiv:1911.11344"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768433\/10562342.pdf?arnumber=10562342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:48:22Z","timestamp":1732736902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10562342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":76,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3416732","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}