{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:56:56Z","timestamp":1784300216768,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["62122018"],"award-info":[{"award-number":["62122018"]}],"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":["62020106008"],"award-info":[{"award-number":["62020106008"]}],"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":["U22A2097"],"award-info":[{"award-number":["U22A2097"]}],"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":["U23A20315"],"award-info":[{"award-number":["U23A20315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Kuaishou"},{"DOI":"10.13039\/501100001809","name":"SongShan Laboratory","doi-asserted-by":"publisher","award":["YYJC012022019"],"award-info":[{"award-number":["YYJC012022019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3429192","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T17:44:52Z","timestamp":1721151892000},"page":"11954-11964","source":"Crossref","is-referenced-by-count":12,"title":["Ump: Unified Modality-Aware Prompt Tuning for Text-Video Retrieval"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1015-7338","authenticated-orcid":false,"given":"Haonan","family":"Zhang","sequence":"first","affiliation":[{"name":"Center for Future Media and the 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\/0000-0002-0672-3790","authenticated-orcid":false,"given":"Pengpeng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2522-6394","authenticated-orcid":false,"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media and the School of Computer Science and 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\/CVPR52729.2023.00635"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149716"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207910"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01351"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3323491"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295098"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611714"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/266180.266382"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-015-0077-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612427"},{"key":"ref14","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":"ref15","article-title":"Text-video retrieval with global-local semantic consistent learning","author":"Zhang","year":"2024","journal-title":"arXiv:2405.12710"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref18","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv:2210.07225"},{"key":"ref19","article-title":"Unsupervised prompt learning for vision-language models","author":"Huang","year":"2022","journal-title":"arXiv:2204.03649"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref21","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cai"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref23","first-page":"1","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. ICLR","author":"He"},{"key":"ref24","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. NIPS","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01637"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref27","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. NeurIPS","author":"Liang"},{"key":"ref28","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv:1802.03426"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235523"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref31","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019","journal-title":"arXiv:1907.13487"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref37","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.","author":"Jia"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/104"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref42","first-page":"30291","article-title":"Expectation-maximization contrastive learning for compact video-and-language representations","volume-title":"Proc. NeurIPS","volume":"35","author":"Jin"},{"key":"ref43","article-title":"CLIP2 Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref44","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"ref47","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. ICML","volume":"97","author":"Houlsby"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref49","article-title":"MV-adapter: Multimodal video transfer learning for video text retrieval","author":"Jin","year":"2023","journal-title":"arXiv:2301.07868"},{"key":"ref50","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref62","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref63","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref65","first-page":"1","article-title":"CLIP-ViP: Adapting pre-trained image-text model to video-language alignment","volume-title":"Proc. ICLR","author":"Xue"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768851\/10599510.pdf?arnumber=10599510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:47:15Z","timestamp":1732736835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10599510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":65,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3429192","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}