{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T00:13:09Z","timestamp":1785283989078,"version":"3.55.0"},"reference-count":64,"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":[{"name":"National Key Research and Development Program of China","award":["2022YFE0133100"],"award-info":[{"award-number":["2022YFE0133100"]}]},{"name":"Hong Kong RGC General Research Fund","award":["152211\/23E"],"award-info":[{"award-number":["152211\/23E"]}]},{"name":"Hong Kong RGC General Research Fund","award":["15216424\/24E"],"award-info":[{"award-number":["15216424\/24E"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102327"],"award-info":[{"award-number":["62102327"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PolyU Internal Fund","award":["P0043932"],"award-info":[{"award-number":["P0043932"]}]},{"DOI":"10.13039\/100030672","name":"NVIDIA AI Technology Center, University of Florida","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100030672","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521718","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:23:06Z","timestamp":1734981786000},"page":"2293-2303","source":"Crossref","is-referenced-by-count":7,"title":["Vision-Language Meets the Skeleton: Progressively Distillation With Cross-Modal Knowledge for 3D Action Representation Learning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5752-1639","authenticated-orcid":false,"given":"Yang","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1404-7183","authenticated-orcid":false,"given":"Tian","family":"He","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7007-4740","authenticated-orcid":false,"given":"Ling","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0449-4525","authenticated-orcid":false,"given":"Jingcai","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Hu","sequence":"additional","affiliation":[{"name":"No.1 Orthopedic Hospital of Chengdu, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5532-9530","authenticated-orcid":false,"given":"Hong","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00626"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00941"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00234"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref10","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref13","first-page":"49250","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967191"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.233"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3253048"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3129616"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3307933"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405712"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3190020"},{"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","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191686"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00086"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00452"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00935"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01594"},{"key":"ref36","first-page":"78496","article-title":"CWCL: Cross-modal transfer with continuously weighted contrastive loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Srinivasa","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"ref41","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01465"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref46","article-title":"PKU-MMD: A large scale benchmark for continuous multi-modal human action understanding","author":"Chunhui","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01807"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3338410"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612449"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611774"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475307"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25451"},{"issue":"11","key":"ref64","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10812782.pdf?arnumber=10812782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:47:37Z","timestamp":1747158457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521718","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}