{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T01:10:21Z","timestamp":1761181821266,"version":"build-2065373602"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62271485"],"award-info":[{"award-number":["62271485"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Science and Technology Project","award":["Z231100007423004"],"award-info":[{"award-number":["Z231100007423004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3599096","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:19Z","timestamp":1755197299000},"page":"7557-7569","source":"Crossref","is-referenced-by-count":1,"title":["Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8603-6757","authenticated-orcid":false,"given":"Enming","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6429-1773","authenticated-orcid":false,"given":"Bingke","family":"Zhu","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5049-8092","authenticated-orcid":false,"given":"Yingying","family":"Chen","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1213-1123","authenticated-orcid":false,"given":"Qinghai","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4976-3095","authenticated-orcid":false,"given":"Ming","family":"Tang","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3361181"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358085"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321503"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3297312"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI.2016.0225"},{"article-title":"GPT-4 technical report","year":"2023","author":"Achiam","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"article-title":"Florence: A new foundation model for computer vision","year":"2021","author":"Yuan","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01951-2"},{"key":"ref22","first-page":"36067","article-title":"Glipv2: Unifying localization and vision-language understanding","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","volume":"35","author":"Zhang","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref26","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25363"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"article-title":"Qwen2 technical report","year":"2024","author":"Yang","key":"ref31"},{"article-title":"The llama 3 herd of models","year":"2024","author":"Dubey","key":"ref32"},{"article-title":"The caltech-ucsd birds-200-2011 dataset","year":"2011","author":"Wah","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"article-title":"Fine-grained visual classification of aircraft","year":"2013","author":"Maji","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref44"},{"key":"ref45","first-page":"5389","article-title":"Do ImageNet classifiers generalize to imagenet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11125523.pdf?arnumber=11125523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:38Z","timestamp":1761153938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3599096","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}