{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T15:59:47Z","timestamp":1780761587417,"version":"3.54.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62306125"],"award-info":[{"award-number":["62306125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["2023YFF0905400"],"award-info":[{"award-number":["2023YFF0905400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U2341229"],"award-info":[{"award-number":["U2341229"]}],"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":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3489024","type":"journal-article","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T13:38:48Z","timestamp":1730381928000},"page":"2499-2512","source":"Crossref","is-referenced-by-count":6,"title":["Modality-Consistent Prompt Tuning With Optimal Transport"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2887-8929","authenticated-orcid":false,"given":"Hairui","family":"Ren","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3975-2483","authenticated-orcid":false,"given":"Fan","family":"Tang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0508-5034","authenticated-orcid":false,"given":"Huangjie","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Zhao","sequence":"additional","affiliation":[{"name":"CSIRO’s Data61, Eveleigh, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1329-8403","authenticated-orcid":false,"given":"Dandan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2697-8093","authenticated-orcid":false,"given":"Yi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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.","volume":"139","author":"Radford"},{"key":"ref2","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":"ref3","first-page":"12","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref7","article-title":"Plot: Prompt learning with optimal transport for vision-language models","author":"Chen","year":"2022","journal-title":"arXiv:2210.01253"},{"key":"ref8","article-title":"Tuning multi-mode token-level prompt alignment across modalities","author":"Wang","year":"2023","journal-title":"arXiv:2309.13847"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3412996"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327605"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref12","first-page":"52326","article-title":"Geodesic multi-modal mixup for robust fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Oh"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2012.00548"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199682737.001.0001"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume":"338","author":"Villani","year":"2009","journal-title":"Optimal Transport: Old and New"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref21","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref22","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref23","article-title":"Improving GANs using optimal transport","author":"Salimans","year":"2018","journal-title":"arXiv:1803.05573"},{"key":"ref24","article-title":"Neural topic model via optimal transport","author":"Zhao","year":"2020","journal-title":"arXiv:2008.13537"},{"key":"ref25","article-title":"Representing mixtures of word embeddings with mixtures of topic embeddings","author":"Wang","year":"2022","journal-title":"arXiv:2203.01570"},{"key":"ref26","article-title":"Improving sequence-to-sequence learning via optimal transport","author":"Chen","year":"2019","journal-title":"arXiv:1901.06283"},{"key":"ref27","article-title":"Vocabulary learning via optimal transport for neural machine translation","author":"Xu","year":"2020","journal-title":"arXiv:2012.15671"},{"key":"ref28","first-page":"1542","article-title":"Graph optimal transport for cross-domain alignment","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3307554"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369656"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref34","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"2","author":"Cuturi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref38","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","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":"ref48","article-title":"Tip-adapter: Training-free CLIP-adapter for better vision-language modeling","author":"Zhang","year":"2021","journal-title":"arXiv:2111.03930"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.08.026"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10740179.pdf?arnumber=10740179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:45Z","timestamp":1767638445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":49,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3489024","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}