{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T17:12:09Z","timestamp":1792257129644,"version":"4.4.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576315"],"award-info":[{"award-number":["62576315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373329"],"award-info":[{"award-number":["62373329"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Natural Science Foundation","doi-asserted-by":"crossref","award":["LZ25F030003"],"award-info":[{"award-number":["LZ25F030003"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Baima Lake Laboratory Joint Funds of the Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LBMHD24F030002"],"award-info":[{"award-number":["LBMHD24F030002"]}],"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":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3651774","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:02Z","timestamp":1768255442000},"page":"7352-7367","source":"Crossref","is-referenced-by-count":9,"title":["Retrieval-Enhanced Visual Prompt Learning for Few-Shot Classification"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3173-757X","authenticated-orcid":false,"given":"Jintao","family":"Rong","sequence":"first","affiliation":[{"name":"College of Information Engineering and Zhejiang Key Laboratory of Intelligent Perception and Control for Complex Systems, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-614X","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8589-9961","authenticated-orcid":false,"given":"Linlin","family":"Ou","sequence":"additional","affiliation":[{"name":"College of Information Engineering and Zhejiang Key Laboratory of Intelligent Perception and Control for Complex Systems, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2913-8388","authenticated-orcid":false,"given":"Tianxiao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8716-7687","authenticated-orcid":false,"given":"Xinyi","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Information Engineering and Zhejiang Key Laboratory of Intelligent Perception and Control for Complex Systems, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2746-8186","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref3","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref4","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":"ref5","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.","volume":"139","author":"Jia"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref7","article-title":"An empirical study of example forgetting during deep neural network learning","author":"Toneva","year":"2018","journal-title":"arXiv:1812.05159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref9","article-title":"CLIP-adapter: Better vision-language models with feature adapters","author":"Gao","year":"2021","journal-title":"arXiv:2110.04544"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02336"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref14","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv:2210.07225"},{"key":"ref15","article-title":"MaPLe: Multi-modal prompt learning","author":"Khattak","year":"2022","journal-title":"arXiv:2210.03117"},{"key":"ref16","article-title":"Dual modality prompt tuning for vision-language pre-trained model","author":"Xing","year":"2022","journal-title":"arXiv:2208.08340"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"ref19","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Borgeaud"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1736"},{"key":"ref21","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.793"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref24","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv:2312.10997"},{"key":"ref25","article-title":"SuS-X: Training-free name-only transfer of vision-language models","author":"Udandarao","year":"2022","journal-title":"arXiv:2211.16198"},{"key":"ref26","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.307"},{"key":"ref29","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_26"},{"key":"ref31","article-title":"Generalization through memorization: Nearest neighbor language models","author":"Khandelwal","year":"2019","journal-title":"arXiv:1911.00172"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-0114(99)00172-4"},{"key":"ref34","article-title":"Semi-parametric neural image synthesis","author":"Blattmann","year":"2022","journal-title":"arXiv:2204.11824"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3406556"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.432"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref40","article-title":"Prompt-aligned gradient for prompt tuning","author":"Zhu","year":"2022","journal-title":"arXiv:2205.14865"},{"key":"ref41","article-title":"Prompt pre-training with twenty-thousand classes for open-vocabulary visual recognition","author":"Ren","year":"2023","journal-title":"arXiv:2304.04704"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3541960"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327605"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424777"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3429192"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02235"},{"key":"ref50","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":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref58","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref65","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. ICML","author":"Recht"},{"key":"ref66","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref69","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref76","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11339245.pdf?arnumber=11339245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T05:18:05Z","timestamp":1778217485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":79,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3651774","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}