{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T22:44:35Z","timestamp":1786229075740,"version":"3.56.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Academic Research Fund Tier 2","award":["MOE-T2EP20122-0006"],"award-info":[{"award-number":["MOE-T2EP20122-0006"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Artificial Intelligence Singapore Program","award":["AISG2-RP-2021-023"],"award-info":[{"award-number":["AISG2-RP-2021-023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3546840","type":"journal-article","created":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T18:01:06Z","timestamp":1741975266000},"page":"1908-1920","source":"Crossref","is-referenced-by-count":6,"title":["Task-to-Instance Prompt Learning for Vision-Language Models at Test Time"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6917-8654","authenticated-orcid":false,"given":"Zhihe","family":"Lu","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1472-6465","authenticated-orcid":false,"given":"Jiawang","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6352-6523","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9171-9234","authenticated-orcid":false,"given":"Zeyu","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0057-1404","authenticated-orcid":false,"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref6","article-title":"PLOT: Prompt learning with optimal transport for vision-language models","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref8","article-title":"Language-aware soft prompting for vision & language foundation models","volume-title":"Proc. ICLR","author":"Bulat"},{"key":"ref9","article-title":"Prompt-aligned gradient for prompt tuning","author":"Zhu","year":"2022","journal-title":"arXiv:2205.14865"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref11","first-page":"1","article-title":"GraphAdapter: Tuning vision-language models with dual knowledge graph","volume-title":"Proc. NeurIPS","volume":"36","author":"Li"},{"key":"ref12","first-page":"32924","article-title":"Beyond sole strength: Customized ensembles for generalized vision-language models","volume-title":"Proc. ICML","author":"Lu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111121"},{"key":"ref14","first-page":"1","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume-title":"Proc. NeurIPS","author":"Shu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref19","first-page":"1","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref20","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref21","first-page":"1","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref24","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref27","article-title":"Factual probing is [MASK]: Learning vs. Learning to recall","author":"Zhong","year":"2021","journal-title":"arXiv:2104.05240"},{"key":"ref28","first-page":"1","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. ICML","author":"Liang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00460"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00966"},{"key":"ref31","first-page":"1","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. ICML","author":"Sun"},{"key":"ref32","first-page":"1","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"Proc. NeurIPS","author":"Schneider"},{"key":"ref33","first-page":"1","article-title":"MEMO: Test time robustness via adaptation and augmentation","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3295929"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00885"},{"key":"ref36","article-title":"Domain adaptation with adversarial training on penultimate activations","author":"Sun","year":"2022","journal-title":"arXiv:2208.12853"},{"key":"ref37","first-page":"9608","article-title":"Uncertainty reduction for model adaptation in semantic segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Prabhu"},{"key":"ref38","article-title":"RAIN: RegulArization on input and network for black-box domain adaptation","author":"Peng","year":"2022","journal-title":"arXiv:2208.10531"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"ref40","first-page":"1","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. NeurIPS","author":"Sohn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2022.3168570"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475482"},{"key":"ref43","first-page":"1","article-title":"Augmented self-labeling for source-free unsupervised domain adaptation","volume-title":"Proc. NeurIPSW","author":"Yan"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3103390"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_10"},{"key":"ref46","first-page":"1","article-title":"Exploiting the intrinsic neighborhood structure for source-free domain adaptation","volume-title":"Proc. NeurIPS","author":"Yang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981099"},{"key":"ref48","first-page":"1","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref51","first-page":"1","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume-title":"Proc. NeurIPS","author":"Iwasawa"},{"key":"ref52","article-title":"A comprehensive survey on test-time adaptation under distribution shifts","author":"Liang","year":"2023","journal-title":"arXiv:2303.15361"},{"key":"ref53","first-page":"178","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":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref58","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref63","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref64","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref67","first-page":"1","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"Proc. ICML","author":"Recht"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref69","first-page":"1","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00744"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29320"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10925517.pdf?arnumber=10925517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:30:21Z","timestamp":1743640221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10925517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3546840","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}