{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T06:29:09Z","timestamp":1774074549405,"version":"3.50.1"},"reference-count":23,"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":[{"name":"National Key R&amp;D Program of China","award":["2022YFC2302700"],"award-info":[{"award-number":["2022YFC2302700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3528362","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T20:30:45Z","timestamp":1736800245000},"page":"671-675","source":"Crossref","is-referenced-by-count":6,"title":["DPO: Discrete Prompt Optimization for Vision-Language Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5808-7843","authenticated-orcid":false,"given":"Nanhao","family":"Liang","sequence":"first","affiliation":[{"name":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac","year":"2022"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref4","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref9","article-title":"Image super-resolution with text prompt diffusion","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3420083"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref18","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref20","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10839035.pdf?arnumber=10839035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T19:24:51Z","timestamp":1738178691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10839035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3528362","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}