{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:30Z","timestamp":1778051490701,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00318","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3254-3264","source":"Crossref","is-referenced-by-count":0,"title":["CLIP\u2019s Visual Embedding Projector is a Few-shot Cornucopia"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Fahes","sequence":"first","affiliation":[{"name":"Inria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuan-Hung","family":"Vu","sequence":"additional","affiliation":[{"name":"Inria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrei","family":"Bursuc","sequence":"additional","affiliation":[{"name":"Inria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"P\u00e9rez","sequence":"additional","affiliation":[{"name":"Kyutai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raoul","family":"de Charette","sequence":"additional","affiliation":[{"name":"Inria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"Nov","key":"ref1","first-page":"463","article-title":"Rademacher and gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"JMLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7566-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","article-title":"Language models are few-shot learners","volume-title":"NeurIPS","author":"Brown"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","article-title":"PLOT: Prompt learning with optimal transport for vision-language models","volume-title":"ICLR","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02791"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2005.09.012","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"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00562"},{"key":"ref15","article-title":"Distance-based regularisation of deep networks for fine-tuning","volume-title":"ICLR","author":"Gouk"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref21","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"ICML","author":"Houlsby"},{"key":"ref22","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02244"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref29","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"ICLR","author":"Kumar"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref32","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"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":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"NeurIPS","author":"Paszke"},{"key":"ref36","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref37","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh"},{"key":"ref38","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"ICML","author":"Recht"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.626"},{"key":"ref40","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume-title":"NeurIPS","author":"Shu"},{"key":"ref41","article-title":"Clipood: Generalizing clip to out-of-distributions","volume-title":"ICML","author":"Shu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02235"},{"key":"ref43","article-title":"Meta-adapter: An online few-shot learner for vision-language model","volume-title":"NeurIPS","author":"Song"},{"key":"ref44","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02201"},{"key":"ref46","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref47","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"ICLR","author":"Wang"},{"key":"ref48","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"NeurIPS","author":"Wang"},{"key":"ref49","article-title":"A hard-to-beat baseline for training-free CLIP-based adaptation","volume-title":"ICLR","author":"Wang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref60","article-title":"Tuning layernorm in attention: Towards efficient multi-modal LLM finetuning","volume-title":"ICLR","author":"Zhao"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00249"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492444.pdf?arnumber=11492444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:13:59Z","timestamp":1778048039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00318","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}