{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:11:40Z","timestamp":1775596300872,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["2022ZD0160402"],"award-info":[{"award-number":["2022ZD0160402"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20514"],"award-info":[{"award-number":["U21A20514"]}],"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":["62071404"],"award-info":[{"award-number":["62071404"]}],"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":["U25A20531"],"award-info":[{"award-number":["U25A20531"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City","award":["3502Z20241027"],"award-info":[{"award-number":["3502Z20241027"]}]},{"name":"Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City","award":["3502Z20241029"],"award-info":[{"award-number":["3502Z20241029"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3634108","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T18:47:30Z","timestamp":1763491650000},"page":"4316-4329","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Language Enhancement Network Based on Decoupling-Joint Adaptation for Few-Shot Action Recognition"],"prefix":"10.1109","volume":"36","author":[{"given":"Suzhou","family":"Que","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8877-5474","authenticated-orcid":false,"given":"Hanyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9352-6927","authenticated-orcid":false,"given":"Kaiwen","family":"Du","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7160","authenticated-orcid":false,"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6670-3727","authenticated-orcid":false,"given":"Yanwei","family":"Pang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-9786","authenticated-orcid":false,"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102205"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102717"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015051"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3219864"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.226"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref10","first-page":"1","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Qu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232717"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00881"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292519"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00882"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274168"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3435003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25403"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref24","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01416"},{"key":"ref26","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":"ref27","first-page":"1","article-title":"Aim: Adapting image models for efficient video understanding","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yang"},{"key":"ref28","first-page":"26462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Pan"},{"key":"ref29","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition","author":"Bishay","year":"2019","journal-title":"arXiv:1907.09021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00628"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01917-4"},{"key":"ref32","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28361"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3361157"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00633"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01888"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103677"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978855"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447209"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3384875"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521712"},{"key":"ref47","article-title":"MVP-shot: Multi-velocity progressive-alignment framework for few-shot action recognition","author":"Qu","year":"2024","journal-title":"arXiv:2405.02077"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32391"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681062"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref52","first-page":"1","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"He"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0944"},{"key":"ref54","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref55","article-title":"D2ST-adapter: Disentangled-and-deformable spatio-temporal adapter for few-shot action recognition","author":"Pei","year":"2023","journal-title":"arXiv:2312.01431"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112170"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC49280.2020.9152261"},{"key":"ref58","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3175923"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3262670"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02017-7"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3354104"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3533573"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref72","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11251346.pdf?arnumber=11251346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:03:44Z","timestamp":1775592224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11251346\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":72,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3634108","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}