{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:11:47Z","timestamp":1777655507099,"version":"3.51.4"},"reference-count":45,"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":["62322211"],"award-info":[{"award-number":["62322211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Pioneer and Leading Goose R&D Program of Zhejiang Province","award":["2024C01023"],"award-info":[{"award-number":["2024C01023"]}]},{"name":"Pioneer and Leading Goose R&D Program of Zhejiang Province","award":["2024C01107"],"award-info":[{"award-number":["2024C01107"]}]},{"name":"Pioneer and Leading Goose R&D Program of Zhejiang Province","award":["2023C01038"],"award-info":[{"award-number":["2023C01038"]}]},{"name":"Zhejiang Province Natural Science Foundation of China","award":["LDT23F01011F01"],"award-info":[{"award-number":["LDT23F01011F01"]}]},{"name":"Zhejiang Province Natural Science Foundation of China","award":["LD24F020007"],"award-info":[{"award-number":["LD24F020007"]}]},{"name":"Key Laboratory of Intelligent Processing Technology for Digital Music"},{"name":"Zhejiang Conservatory of Music"},{"name":"Ministry of Culture and Tourism","award":["2023DMKLB004"],"award-info":[{"award-number":["2023DMKLB004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3639886","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:18Z","timestamp":1764787398000},"page":"1457-1468","source":"Crossref","is-referenced-by-count":2,"title":["Prompt Learning With Knowledge Regularization for Pre-Trained Vision-Language Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9687-1893","authenticated-orcid":false,"given":"Boyang","family":"Guo","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0790-9279","authenticated-orcid":false,"given":"Jiehua","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8874-241X","authenticated-orcid":false,"given":"Yaoqi","family":"Sun","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3590-0060","authenticated-orcid":false,"given":"Xichun","family":"Sheng","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University, Macao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"950","article-title":"Fast Differentiable Sorting and Ranking","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Blondel","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321503"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16213"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310657"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref10","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref11","first-page":"6757","article-title":"Visual-language prompt tuning with knowledge-guided context optimization","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Xu","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref15","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref17","first-page":"15190","article-title":"Self-regulating prompts: Foundational model adaptation without forgetting","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Uzair","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3144183"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref21","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3617833"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02544"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2448"},{"key":"ref28","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht","year":"2019"},{"key":"ref29","first-page":"1","article-title":"Consistency-guided prompt learning for vision-language models","author":"Roy"},{"key":"ref30","first-page":"618","article-title":"Grad-Cam: Visual explanations from deep networks via gradient-based localization","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Ramprasaath","year":"2017"},{"key":"ref31","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref32","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref36","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2022"},{"key":"ref37","article-title":"A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310282"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref41","first-page":"493","article-title":"TIP-Adapter: Training-free clip-adapter for better vision-language modeling","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhang","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11275895.pdf?arnumber=11275895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:23Z","timestamp":1773086363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11275895\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3639886","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}