{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:18:43Z","timestamp":1792786723179,"version":"4.5.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key R&D Program of Zhejiang Province","award":["2026C01016"],"award-info":[{"award-number":["2026C01016"]}]},{"name":"National Natural Science Foundation of China","award":["62576313"],"award-info":[{"award-number":["62576313"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQN26F020039"],"award-info":[{"award-number":["LQN26F020039"]}],"id":[{"id":"https:\/\/ror.org\/04aqat463","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Key R&D Program of Ningbo","award":["2025Z128"],"award-info":[{"award-number":["2025Z128"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tai.2026.3686093","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:50:57Z","timestamp":1777405857000},"page":"5404-5416","source":"Crossref","is-referenced-by-count":0,"title":["MetaFusion: Instance-Aware Meta-Prompting and Token Refinement for VLMs Generalization"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2909-7702","authenticated-orcid":false,"given":"Mushui","family":"Liu","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"],"department":["College of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6091-5352","authenticated-orcid":false,"given":"Fangtai","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"],"department":["College of Information Science and Electronic Engineering and National Key Laboratory of Millimeter-Wave and Terahertz Remote Sensing"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3579-9130","authenticated-orcid":false,"given":"Ziqian","family":"Lu","sequence":"additional","affiliation":[{"name":"Zhejiang Sci-Tech University","place":["Zhejiang, China"],"department":["School of Computer Science and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7144-1511","authenticated-orcid":false,"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Ningbo, China"],"department":["Ningbo Innovation Center"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0294-2099","authenticated-orcid":false,"given":"Yunlong","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"],"department":["College of Information Science and Electronic Engineering and National Key Laboratory of Millimeter-Wave and Terahertz Remote Sensing"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4361-956X","authenticated-orcid":false,"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"],"department":["Department of Automation"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5098-2506","authenticated-orcid":false,"given":"Zhongfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Watson School, State University of New York Binghamton University","place":["Binghamton, NY, USA"],"department":["Computer Science Department"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford","year":"2021"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521671"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3397191"},{"key":"ref7","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240499"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref13","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_18"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27853"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"ref23","article-title":"Mixture of prompt learning for vision language models","author":"Du","year":"2024"},{"key":"ref24","article-title":"Prompt diffusion robustifies any-modality prompt learning","author":"Du","year":"2024"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3392941"},{"key":"ref27","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0444"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01776"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4372"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01493"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10915-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref41","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref43","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref46","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. ICML","author":"Recht","year":"2019"},{"key":"ref47","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3432753"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3468884"},{"key":"ref52","article-title":"Aptos 2019 blindness detection dataset","year":"2019"},{"key":"ref53","article-title":"ISIC 2019 dataset","year":"2019"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11719381\/11498633.pdf?arnumber=11498633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T19:07:55Z","timestamp":1791227275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11498633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":53,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tai.2026.3686093","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}