{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:44Z","timestamp":1777865384448,"version":"3.51.4"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["U24B20180"],"award-info":[{"award-number":["U24B20180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00241","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2501-2511","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Multimodal Prototype Learning in Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Xingyu","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beier","family":"Zhu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miaoge","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfan","family":"Li","sequence":"additional","affiliation":[{"name":"Sichuan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfeng","family":"Fang","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicai","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Multimodality helps few-shot 3d point cloud semantic segmentation","author":"An","year":"2024","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","article-title":"PLOT: prompt learning with optimal transport for vision-language models","volume-title":"ICLR","author":"Chen","year":"2023"},{"key":"ref5","article-title":"Graph optimal transport for cross-domain alignment","volume-title":"ICML","author":"Chen","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"ref8","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"Cuturi","year":"2013","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2004.383","article-title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories","volume-title":"CVPR Workshops","author":"Fei-Fei","year":"2004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2636"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0507"},{"key":"ref14","article-title":"DOTA: distributional test-time adaptation of vision-language models","author":"Han","year":"2024","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref19","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02776"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00863"},{"key":"ref24","article-title":"Visual-text cross alignment: Refining the similarity score in vision-language models","volume-title":"ICML","author":"Li","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01408"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/624"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref28","article-title":"Patch-prompt aligned bayesian prompt tuning for vision-language models","volume-title":"UAI","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"CoRR"},{"key":"ref30","article-title":"Visual classification via description from large language models","volume-title":"ICLR","author":"Menon","year":"2023"},{"key":"ref31","article-title":"Meta-prompting for automating zero-shot visual recognition with 11 ms","volume-title":"ECCV","author":"Jehanzeb Mirza","year":"2024"},{"key":"ref32","first-page":"666","article-title":"M\u00e9moire sur la th\u00e9orie des d\u00e9blais et des remblais","author":"Monge","journal-title":"Mem. Math. Phys. Acad. Royale Sci."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref35","article-title":"LMM-R1: empowering 3b lmms with strong reasoning abilities through two-stage rule-based RL","author":"Peng","year":"2025","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.31"},{"key":"ref38","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref39","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"ICML","author":"Recht","year":"2019"},{"key":"ref40","article-title":"Doublebounded optimal transport for advanced clustering and classification","volume-title":"AAAI","author":"Shi","year":"2024"},{"key":"ref41","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","author":"Shu","year":"2022","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref43","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref44","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"ICLR","author":"Wang","year":"2021"},{"key":"ref45","article-title":"Tuning multi-mode tokenlevel prompt alignment across modalities","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.107"},{"key":"ref50","article-title":"Exploring diverse in-context configurations for image captioning","volume-title":"NeurIPS","author":"Yang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02106-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4084-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2659647"},{"key":"ref54","article-title":"C-TPT: calibrated test-time prompt tuning for vision-language models via text feature dispersion","volume-title":"ICLR","author":"Suk Yoon","year":"2024"},{"key":"ref55","article-title":"Dual prototype evolving for test-time generalization of visionlanguage models","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref60","article-title":"Robust finetuning of zero-shot models via variance reduction","author":"Zhu","year":"2025","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02373"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00887"},{"key":"ref63","article-title":"Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting","author":"Zhu","year":"2024","journal-title":"NeurIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680885"},{"key":"ref65","article-title":"AWT: transferring vision-language models via augmentation, weighting, and transportation","author":"Zhu","year":"2024","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446066.pdf?arnumber=11446066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:24:00Z","timestamp":1777530240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00241","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}