{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T12:48:15Z","timestamp":1791982095415,"version":"4.4.0"},"reference-count":30,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476048"],"award-info":[{"award-number":["62476048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFA1004100"],"award-info":[{"award-number":["2022YFA1004100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011381"],"award-info":[{"award-number":["2024A1515011381"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.inffus.2025.103798","type":"journal-article","created":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T02:29:07Z","timestamp":1759544947000},"page":"103798","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PB","title":["Decoupled prompt learning guided by chain-of-task"],"prefix":"10.1016","volume":"127","author":[{"given":"Zongqian","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengmeng","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9366-6586","authenticated-orcid":false,"given":"Zhengxia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6840-0578","authenticated-orcid":false,"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2025.103798_bib0001","series-title":"ICML","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.inffus.2025.103798_bib0002","series-title":"ICML","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.inffus.2025.103798_bib0003","unstructured":"J. Zhang, S. Wu, L. Gao, H. Shen, J. Song, Dept: decoupled prompt tuning, arXiv: 2309.07439(2023)."},{"key":"10.1016\/j.inffus.2025.103798_bib0004","series-title":"ICCV","first-page":"15190","article-title":"Self-regulating prompts: foundational model adaptation without forgetting","author":"Khattak","year":"2023"},{"key":"10.1016\/j.inffus.2025.103798_bib0005","unstructured":"Z. Wu, Y. Liu, M. Zhan, J. Shen, P. Hu, X. Zhu, Adaptive multi-modality prompt learning, arXiv: 2312.00823(2023)."},{"key":"10.1016\/j.inffus.2025.103798_bib0006","series-title":"NeurIPS","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022"},{"key":"10.1016\/j.inffus.2025.103798_bib0007","series-title":"CVPR","first-page":"19113","article-title":"Maple: multi-modal prompt learning","author":"Khattak","year":"2023"},{"key":"10.1016\/j.inffus.2025.103798_bib0008","series-title":"CVPR","first-page":"16816","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"key":"10.1016\/j.inffus.2025.103798_bib0009","series-title":"CVPR","first-page":"14084","article-title":"Learning to prompt for open-vocabulary object detection with vision-language model","author":"Du","year":"2022"},{"key":"10.1016\/j.inffus.2025.103798_bib0010","series-title":"CVPR","first-page":"10867","article-title":"From images to textual prompts: zero-shot visual question answering with frozen large language models","author":"Guo","year":"2023"},{"issue":"9","key":"10.1016\/j.inffus.2025.103798_bib0011","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2025.103798_bib0012","series-title":"ECCV","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.inffus.2025.103798_bib0013","unstructured":"Y. Zang, W. Li, K. Zhou, C. Huang, C.C. Loy, Unified vision and language prompt learning, arXiv: 2210.07225(2022)."},{"key":"10.1016\/j.inffus.2025.103798_bib0014","series-title":"WACV","first-page":"5656","article-title":"Multitask vision-language prompt tuning","author":"Shen","year":"2024"},{"key":"10.1016\/j.inffus.2025.103798_bib0015","unstructured":"N. Ho, L. Schmid, S.-Y. Yun, Large language models are reasoning teachers, arXiv: 2212.10071(2022)."},{"key":"10.1016\/j.inffus.2025.103798_bib0016","series-title":"ICLR","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022"},{"key":"10.1016\/j.inffus.2025.103798_bib0017","unstructured":"Y. Yang, C. Zhang, Z. Yang, Y. Gao, Y. Qin, K. Li, X. Sun, J. Yang, Y. Gu, RESTORE: towards feature shift for vision-language prompt learning, arXiv: 2403.06136(2024)."},{"key":"10.1016\/j.inffus.2025.103798_bib0018","series-title":"CVPR","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2025.103798_bib0019","series-title":"COLT","first-page":"164","article-title":"PAC-Bayesian model averaging","author":"McAllester","year":"1999"},{"key":"10.1016\/j.inffus.2025.103798_bib0020","unstructured":"V. Akinwande, Y. Jiang, D. Sam, J.Z. Kolter, Understanding prompt engineering may not require rethinking generalization, arXiv: 2310.03957(2023)."},{"key":"10.1016\/j.inffus.2025.103798_bib0021","series-title":"ICML","first-page":"25407","article-title":"Improving out-of-distribution robustness via selective augmentation","author":"Yao","year":"2022"},{"key":"10.1016\/j.inffus.2025.103798_bib0022","series-title":"CVPR","first-page":"3498","article-title":"Cats and dogs","author":"Parkhi","year":"2012"},{"key":"10.1016\/j.inffus.2025.103798_bib0023","series-title":"2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing","first-page":"722","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"key":"10.1016\/j.inffus.2025.103798_bib0024","series-title":"ECCV","first-page":"446","article-title":"Food-101\u2013mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.inffus.2025.103798_bib0025","unstructured":"S. Maji, E. Rahtu, J. Kannala, M. Blaschko, A. Vedaldi, Fine-grained visual classification of aircraft, arXiv: 1306.5151(2013)."},{"key":"10.1016\/j.inffus.2025.103798_bib0026","series-title":"CVPR Workshop","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"},{"issue":"7","key":"10.1016\/j.inffus.2025.103798_bib0027","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"Eurosat: a novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.inffus.2025.103798_bib0028","series-title":"CVPR","first-page":"3606","article-title":"Describing textures in the wild","author":"Cimpoi","year":"2014"},{"issue":"11","key":"10.1016\/j.inffus.2025.103798_bib0029","article-title":"A dataset of 101 human action classes from videos in the wild","volume":"2","author":"Soomro","year":"2012","journal-title":"Center Res. Comput. Vision"},{"key":"10.1016\/j.inffus.2025.103798_bib0030","series-title":"CVPR","first-page":"3485","article-title":"Sun database: large-scale scene recognition from abbey to zoo","author":"Xiao","year":"2010"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253525008607?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253525008607?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:26:28Z","timestamp":1773811588000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253525008607"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":30,"alternative-id":["S1566253525008607"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2025.103798","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Decoupled prompt learning guided by chain-of-task","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2025.103798","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103798"}}