{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T08:51:20Z","timestamp":1764838280429,"version":"3.46.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"name":"National Key Research and Development Program of China","award":["2024YFB3312900"],"award-info":[{"award-number":["2024YFB3312900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441617"],"award-info":[{"award-number":["62441617"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2025-00057"],"award-info":[{"award-number":["226-2025-00057"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ningbo Yongjiang Talent Introduction Programme","award":["2024A-401-G"],"award-info":[{"award-number":["2024A-401-G"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3604454","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:30:52Z","timestamp":1756755052000},"page":"219-235","source":"Crossref","is-referenced-by-count":0,"title":["Structure-Induced Gradient Regulation for Generalizable Vision-Language Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-1291","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9705-5398","authenticated-orcid":false,"given":"Minghe","family":"Gao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longhui","family":"Wei","sequence":"additional","affiliation":[{"name":"Huawei, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6142-9914","authenticated-orcid":false,"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"article-title":"Visual prompting: Modifying pixel space to adapt pre-trained models","year":"2022","author":"Bahng","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27918"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref9","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"article-title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","year":"2022","author":"Grootendorst","key":"ref10"},{"article-title":"Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization","year":"2023","author":"Hassan","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"key":"ref16","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref18","first-page":"143","article-title":"A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization","volume-title":"Proc. 14th Int. Conf. Mach. Learn.","author":"Joachims","year":"1997"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00241"},{"key":"ref23","first-page":"7290","article-title":"Fine-grained semantically aligned vision-language pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref24","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01214"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02211"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.596"},{"article-title":"WebVision database: Visual learning and understanding from web data","year":"2017","author":"Li","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Fine-grained visual classification of aircraft","year":"2013","author":"Maji","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00205"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"article-title":"A simple neural attentive meta-learner","year":"2017","author":"Mishra","key":"ref33"},{"key":"ref34","first-page":"76298","article-title":"LoCoOp: Few-shot out-of-distribution detection via prompt learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Miyai"},{"key":"ref35","first-page":"2554","article-title":"Meta networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Munkhdalai"},{"article-title":"On first-order meta-learning algorithms","year":"2018","author":"Nichol","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref38","first-page":"721","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oreshkin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"8","key":"ref41","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref42","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2017"},{"key":"ref43","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref45","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01857"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref48","first-page":"14274","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02700"},{"key":"ref53","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref54","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"article-title":"C-TPT: Calibrated test-time prompt tuning for vision-language models via text feature dispersion","year":"2024","author":"Yoon","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20243"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01435"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11145877.pdf?arnumber=11145877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T08:47:09Z","timestamp":1764838029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11145877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":60,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3604454","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}