{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:07:26Z","timestamp":1777889246031,"version":"3.51.4"},"reference-count":56,"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\/iccv51701.2025.00144","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":["One Last Attention for Your Vision-Language Model"],"prefix":"10.1109","author":[{"given":"Liang","family":"Chen","sequence":"first","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ghazi Shazan","family":"Ahmad","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjun","family":"Yao","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Shen","sequence":"additional","affiliation":[{"name":"MBZUAI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3525"},{"key":"ref2","article-title":"Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","author":"Barbu","year":"2019","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02315"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00168"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3269"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02061-3"},{"key":"ref8","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2023","journal-title":"ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.179"},{"key":"ref13","article-title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories","author":"Fei-Fei","year":"2004","journal-title":"CVPRW"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01853"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref19","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref23","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","author":"Kumar","year":"2022","journal-title":"ICLR"},{"key":"ref24","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref25","article-title":"Ttt++: When does self-supervised test-time training fail or thrive?","author":"Liu","year":"2021","journal-title":"NeurIPS"},{"key":"ref26","volume-title":"A simple long-tailed recognition baseline via vision-language model","author":"Ma","year":"2021"},{"key":"ref27","volume-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref29","article-title":"Cats and dogs","author":"Omkar","year":"2012","journal-title":"CVPR"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref31","article-title":"Do imagenet classifiers generalize to imagenet?","author":"Recht","year":"2019","journal-title":"ICML"},{"key":"ref32","article-title":"Towards parameter-efficient integration of pretrained language models in temporal video grounding","author":"Erica","year":"2023","journal-title":"ACL Findings"},{"key":"ref33","article-title":"Testtime prompt tuning for zero-shot generalization in visionlanguage models","author":"Shu","year":"2022","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref35","article-title":"Test-time training with selfsupervision for generalization under distribution shifts","author":"Sun","year":"2020","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref37","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"Wang","year":"2021","journal-title":"ICLR"},{"key":"ref39","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref42","article-title":"Explicit inductive bias for transfer learning with convolutional networks","author":"Xuhong","year":"2018","journal-title":"ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref45","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2022","journal-title":"ICLR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781139481335.006"},{"key":"ref47","volume-title":"On the test-time zeroshot generalization of vision-language models: Do we really need prompt learning? In CVPR","author":"Zanella","year":"2024"},{"key":"ref48","volume-title":"Unified vision and language prompt learning","author":"Zang","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref51","article-title":"Tip-adapter: Training-free clip-adapter for better visionlanguage modeling","author":"Zhang","year":"2022","journal-title":"ECCV"},{"key":"ref52","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Machine Learning for Healthcare Conference","author":"Zhang","year":"2022"},{"key":"ref53","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2024","journal-title":"ICLR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"}],"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\/11444681.pdf?arnumber=11444681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:10:14Z","timestamp":1777612214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00144","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}