{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:54:16Z","timestamp":1777888456413,"version":"3.51.4"},"reference-count":36,"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\/501100001863","name":"New Energy and Industrial Technology Development Organization (NEDO)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001863","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\/iccv51701.2025.01660","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Mainak","family":"Singha","sequence":"first","affiliation":[{"name":"University of Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhankar","family":"Roy","sequence":"additional","affiliation":[{"name":"University of Bergamo,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarthak","family":"Mehrotra","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankit","family":"Jha","sequence":"additional","affiliation":[{"name":"LNMIIT,Jaipur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moloud","family":"Abdar","sequence":"additional","affiliation":[{"name":"The University of Queensland,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biplab","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02576"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref6","article-title":"search of lost domain generalization","volume-title":"International Conference on Learning Representations","author":"Gulrajani","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3302410"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref9","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref10","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01155"},{"key":"ref15","article-title":"Fedclip: Fast generalization and personalization for clip in federated learning","volume-title":"ICLR Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models","author":"Lu","year":"2023"},{"key":"ref16","first-page":"1273","article-title":"Communicationefficient learning of deep networks from decentralized data","volume-title":"Artificial intelligence and statistics","author":"McMahan","year":"2017"},{"key":"ref17","article-title":"Visual classification via description from large language models","volume-title":"International Conference on Learning Representations","author":"Menon","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403176"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref21","article-title":"Federated text-driven prompt generation for visionlanguage models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qiu"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref23","first-page":"694","article-title":"Lightsecagg: a lightweight and versatile design for secure aggregation in federated learning","volume":"4","author":"So","year":"2022","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_13"},{"key":"ref25","first-page":"676","article-title":"Understanding generalization of federated learning via stability: Heterogeneity matters","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Sun"},{"key":"ref26","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00653"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2018.8698609"},{"key":"ref32","article-title":"Federated learning with additional mechanisms on clients to reduce communication costs","volume-title":"arXiv preprint","author":"Yao","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611781"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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\/11443561.pdf?arnumber=11443561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:44:17Z","timestamp":1777610657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443561\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01660","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}