{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T08:20:04Z","timestamp":1785313204550,"version":"3.55.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62202204"],"award-info":[{"award-number":["62202204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JUSRP123032"],"award-info":[{"award-number":["JUSRP123032"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668503","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"5748-5757","source":"Crossref","is-referenced-by-count":1,"title":["Beyond Mere Tuning: Harnessing the Full Potential of Prompts for Text-Video Retrieval"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-0918","authenticated-orcid":false,"given":"Donglin","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwen","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"Centre for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8110-9205","authenticated-orcid":false,"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3396272"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149716"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3446774"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355644"},{"key":"ref5","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88007-1_43"},{"key":"ref7","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239183"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-024-00335-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401132"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3140656"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3572032"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2196"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref23","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref25","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":"ref26","first-page":"38728","article-title":"MPLUG-2: A modularized multi-modal foundation model across text, image and video","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01622"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680839"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00331"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112145"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25113"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3574925"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3429192"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0867"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25597"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.427"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3393843"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref49","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cai","year":"2020"},{"key":"ref50","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref52","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"ref58","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16837"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11417280.pdf?arnumber=11417280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T05:19:15Z","timestamp":1784265555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668503","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}