{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:11:30Z","timestamp":1781075490128,"version":"3.54.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022TQ0315"],"award-info":[{"award-number":["2022TQ0315"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQN25F010015"],"award-info":[{"award-number":["LQN25F010015"]}]},{"name":"Tianmushan Laboratory","award":["TK-2024-D-009"],"award-info":[{"award-number":["TK-2024-D-009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tii.2025.3577686","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T13:46:35Z","timestamp":1750945595000},"page":"7643-7652","source":"Crossref","is-referenced-by-count":3,"title":["TransCLIP: Transferring Vision\u2013Language Models for Efficient Video Action Recognition"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3737-3201","authenticated-orcid":false,"given":"Wen","family":"Wang","sequence":"first","affiliation":[{"name":"Tianmushan Laboratory, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3377-469X","authenticated-orcid":false,"given":"Yanzhou","family":"Su","sequence":"additional","affiliation":[{"name":"Fuzhou University, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7626-1077","authenticated-orcid":false,"given":"Jason","family":"Gu","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Dalhousie University, Halifax, NS, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3018487"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3264284"},{"key":"ref3","article-title":"Clip2video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref5","first-page":"16664","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref7","first-page":"26462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612490"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00633"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01755"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref22","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref24","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9424\/11174041\/11053123.pdf?arnumber=11053123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:14:08Z","timestamp":1762539248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11053123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":30,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tii.2025.3577686","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}