{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T20:05:55Z","timestamp":1784318755699,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["62577001"],"award-info":[{"award-number":["62577001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3706961","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:38:27Z","timestamp":1782934707000},"page":"7428-7443","source":"Crossref","is-referenced-by-count":0,"title":["Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3824-687X","authenticated-orcid":false,"given":"Shanshan","family":"Wang","sequence":"first","affiliation":[{"name":"National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7295-5960","authenticated-orcid":false,"family":"ALuSi","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-0237","authenticated-orcid":false,"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-4257","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5052-000X","authenticated-orcid":false,"given":"Xingyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3512354"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3523801"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3568747"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2948480"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2765836"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611725"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02106-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108993"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4084-6"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381337"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535400"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3473532"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3546840"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3525"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"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":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref23","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"Wang","year":"2020","journal-title":"arXiv:2006.10726"},{"key":"ref24","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume-title":"Proc. NeurIPS","volume":"34","author":"Iwasawa"},{"key":"ref25","first-page":"41647","article-title":"Adanpc: Exploring non-parametric classifier for test-time adaptation","volume-title":"Proc. Int. Conf.  Mach. Learn.","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29611"},{"key":"ref28","article-title":"DynaPrompt: Dynamic test-time prompt tuning","author":"Xiao","year":"2025","journal-title":"arXiv:2501.16404"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/991635.991706"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3676383"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLT65785.2025.11193278"},{"key":"ref33","article-title":"Backpropagation-free test-time adaptation via probabilistic Gaussian alignment","author":"Zhang","year":"2025","journal-title":"arXiv:2508.15568"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754947"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00090"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888937"},{"key":"ref37","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2023","journal-title":"arXiv:2305.18010"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_8"},{"key":"ref42","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv:2210.07183"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_21"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1010"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref49","first-page":"5389","article-title":"Do imagenet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref51","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. NeurIPS","volume":"32","author":"Wang"},{"key":"ref52","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref65","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680652"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3595896"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38110"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586118"},{"key":"ref72","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","author":"Qu","year":"2025","journal-title":"arXiv:2502.06501"},{"key":"ref73","article-title":"Locality-aware cross-modal correspondence learning for dense audio-visual events localization","author":"Xing","year":"2024","journal-title":"arXiv:2409.07967"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11589538.pdf?arnumber=11589538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T19:47:05Z","timestamp":1784317625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11589538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3706961","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}