{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:08:51Z","timestamp":1780636131726,"version":"3.54.1"},"reference-count":58,"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\/iccv51701.2025.00824","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8810-8819","source":"Crossref","is-referenced-by-count":1,"title":["Test-Time Retrieval-Augmented Adaptation for Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Xinqi","family":"Fan","sequence":"first","affiliation":[{"name":"Manchester Metropolitan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueli","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong Metropolitan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luoxiao","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi'an University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuin Hong","family":"Yap","sequence":"additional","affiliation":[{"name":"Manchester Metropolitan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rizwan","family":"Qureshi","sequence":"additional","affiliation":[{"name":"University of Central Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moi Hoon","family":"Yap","sequence":"additional","affiliation":[{"name":"Manchester Metropolitan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[{"name":"University of Central Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 3. 2: Revolutionizing edge ai and vision with open, customizable models","year":"2024","journal-title":"Meta AI Report"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref7","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4099"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref12","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"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","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref19","article-title":"RA-TTA: Retrieval-augmented test-time adaptation for vision-language models","volume-title":"International Conference on Learning Representations","author":"Lee"},{"key":"ref20","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"6028","article-title":"Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation","volume-title":"International conference on machine learning","author":"Liang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02181-w"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1280"},{"key":"ref25","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"35719","article-title":"Understanding retrievalaugmented task adaptation for vision-language models","volume-title":"International Conference on Machine Learning","author":"Ming"},{"key":"ref28","article-title":"Evaluating prediction-time batch normalization for robustness under covariate shift","author":"Nado","year":"2020","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref30","article-title":"Towards stable test-time adaptation in dynamic wild world","volume-title":"Internetional Conference on Learning Representations","author":"Niu"},{"key":"ref31","article-title":"Gpt-4v(ision) system card","year":"2023","journal-title":"OpenAI Technical Report"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref33","article-title":"Thinking beyond tokens: From brain-inspired intelligence to cognitive foundations for artificial general intelligence and its societal impact","author":"Qureshi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref35","article-title":"Learning mixture of gaussians with streaming data","volume":"30","author":"Raghunathan","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"International Conference on Machine Learning","author":"Recht"},{"key":"ref37","article-title":"Improving robustness against common corruptions by covariate shift adaptation","author":"Schneider","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_37"},{"key":"ref42","first-page":"9229","article-title":"Test-time training with selfsupervision for generalization under distribution shifts","volume-title":"International Conference on Machine Learning","author":"Sun"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2861"},{"key":"ref46","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref47","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref49","first-page":"29393","article-title":"Exploiting the intrinsic neighborhood structure for source-free domain adaptation","volume":"34","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","article-title":"Filip: Fine-grained interactive language-image pre-training","volume-title":"International Conference on Learning Representations","author":"Yao"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02245"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2040"}],"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\/11445577.pdf?arnumber=11445577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:17:39Z","timestamp":1777612659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00824","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}