{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:38:03Z","timestamp":1778603883767,"version":"3.51.4"},"reference-count":57,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00220","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2281-2291","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haotian","family":"Zhai","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiupeng","family":"Shi","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruirui","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref9","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3460180"},{"key":"ref11","article-title":"Ranked entropy minimization for continual test-time adaptation","author":"Han","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01512"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref17","article-title":"Beyond entropy: Region confidence proxy for wild test-time adaptation","author":"Hu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","volume":"1","author":"Jia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref22","article-title":"Entropy is not enough for test-time adaptation: From the perspective of disentangled factors","volume":"1","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02181-w"},{"key":"ref25","article-title":"Fine-grained visual classification of aircraft","volume":"2","author":"Maji","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32652"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref29","article-title":"Bidirectional prototype-reward co-evolution for test-time adaptation of vision-language models","author":"Qiao","year":"2025","journal-title":"arXiv preprint arXiv"},{"issue":"2","key":"ref30","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","volume":"1","author":"Radford"},{"key":"ref31","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"International Conference on Machine Learning","author":"Recht"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02788"},{"key":"ref33","article-title":"Testtime prompt tuning for zero-shot generalization in visionlanguage models","author":"Shu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00090"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00126"},{"key":"ref37","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","article-title":"Fully test-time adaptation by entropy minimization","author":"Wang","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111300"},{"key":"ref41","article-title":"Learning robust global representations by penalizing local predictive power","volume":"32","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref45","article-title":"C-tpt: Calibrated test-time prompt tuning for visionlanguage models via text feature dispersion","author":"Suk Yoon","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209257"},{"key":"ref48","article-title":"Dual prototype evolving for test-time generalization of vision-language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00576"},{"key":"ref50","article-title":"Historical test-time prompt tuning for vision foundation models","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2799"},{"key":"ref52","article-title":"Tip-adapter: Training-free clip-adapter for better visionlanguage modeling","author":"Zhang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Boostadapter: Improving visionlanguage test-time adaptation via regional bootstrapping","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28568"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref57","article-title":"Efficient test-time prompt tuning for vision-language models","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11444253.pdf?arnumber=11444253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:12Z","timestamp":1777529832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00220","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}