{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T09:23:55Z","timestamp":1781169835379,"version":"3.54.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62072190"],"award-info":[{"award-number":["62072190"]}],"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":["U24A20327"],"award-info":[{"award-number":["U24A20327"]}],"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":["U23B2013"],"award-info":[{"award-number":["U23B2013"]}],"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":["62276176"],"award-info":[{"award-number":["62276176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2024A1515010900"],"award-info":[{"award-number":["2024A1515010900"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3586487","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:47:51Z","timestamp":1752860871000},"page":"4602-4617","source":"Crossref","is-referenced-by-count":3,"title":["Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9550-7666","authenticated-orcid":false,"given":"Kai","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6877-3825","authenticated-orcid":false,"given":"Shuhai","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3808-5650","authenticated-orcid":false,"given":"Zeng","family":"You","sequence":"additional","affiliation":[{"name":"School of Future Technology, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-8578","authenticated-orcid":false,"given":"Jinwu","family":"Hu","sequence":"additional","affiliation":[{"name":"Pazhou Laboratory, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-756X","authenticated-orcid":false,"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9415-0496","authenticated-orcid":false,"given":"Fei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref6","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":"Zhan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2912357"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3086590"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2508600"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2914577"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273459"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9692-3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9666948"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/BIOCAS.2019.8919127"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00232"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-019-01301-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2837386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413941"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051495"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3104182"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3230249"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378886"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0983-5"},{"key":"ref30","article-title":"Skeleton based zero shot action recognition in joint pose-language semantic space","author":"Jasani","year":"2019","journal-title":"arXiv:1911.11344"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506179"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611888"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01775"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref35","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC49280.2020.9152261"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385286"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_21"},{"key":"ref43","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Iwasawa"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298186"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.233"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2019.8909840"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20191"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","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":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475473"},{"key":"ref56","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Frome"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999959"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref63","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3354104"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref68","first-page":"26007","article-title":"Semi-supervised semantic segmentation with prototype-based consistency regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref69","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref70","first-page":"842","article-title":"Large margin deep networks for classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Elsayed"},{"key":"ref71","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","author":"Khosla"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104392"},{"key":"ref73","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref74","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"issue":"46","key":"ref75","first-page":"1345","article-title":"Clustering on the unit hypersphere using von Mises-Fisher distributions","volume":"6","author":"Banerjee","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1080\/03610919408813161"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3365212"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"ref81","article-title":"MiniCPM: Unveiling the potential of small language models with scalable training strategies","author":"Hu","year":"2024","journal-title":"arXiv:2404.06395"},{"key":"ref82","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"DeepSeek-AI","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00514"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3363831"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3410301"},{"issue":"86","key":"ref88","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1002\/0471725293"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11083680.pdf?arnumber=11083680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:58:07Z","timestamp":1753379887000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11083680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3586487","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}