{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T10:08:32Z","timestamp":1780567712171,"version":"3.54.1"},"reference-count":74,"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\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62225605"],"award-info":[{"award-number":["62225605"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12326608"],"award-info":[{"award-number":["12326608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LD24F020016"],"award-info":[{"award-number":["LD24F020016"]}]},{"name":"Natural Science Foundation of Shanghai","award":["24ZR1425600"],"award-info":[{"award-number":["24ZR1425600"]}]},{"name":"Ningbo Science and Technology Special Projects","award":["2025Z028"],"award-info":[{"award-number":["2025Z028"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission","doi-asserted-by":"publisher","award":["24CGA73"],"award-info":[{"award-number":["24CGA73"]}],"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":[[2025]]},"DOI":"10.1109\/tip.2025.3573498","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T13:45:37Z","timestamp":1749735937000},"page":"5215-5227","source":"Crossref","is-referenced-by-count":4,"title":["Decoupling Discriminative Attributes for Few-Shot Fine-Grained Recognition"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7544-910X","authenticated-orcid":false,"given":"Yehao","family":"Lu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3322-4273","authenticated-orcid":false,"given":"Chaoxiang","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1417-7884","authenticated-orcid":false,"given":"Wei","family":"Su","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9943-1577","authenticated-orcid":false,"given":"Guangcong","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9380-5172","authenticated-orcid":false,"given":"Wenjie","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3414-8754","authenticated-orcid":false,"given":"Xuewei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Information, Shanghai Dianji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3023-1662","authenticated-orcid":false,"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"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. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref3","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022","journal-title":"arXiv:2210.07183"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref5","article-title":"Beyond sole strength: Customized ensembles for generalized vision-language models","author":"Lu","year":"2023","journal-title":"arXiv:2311.17091"},{"key":"ref6","article-title":"Follow-up differential descriptions: Language models resolve ambiguities for image classification","author":"Esfandiarpoor","year":"2023","journal-title":"arXiv:2311.07593"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3267621"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3143692"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref15","article-title":"GIST: Generating image-specific text for fine-grained object classification","author":"Lewis","year":"2023","journal-title":"arXiv:2307.11315"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3443394"},{"key":"ref17","article-title":"FD-align: Feature discrimination alignment for fine-tuning pre-trained models in few-shot learning","volume-title":"Proc. NeurIPS","author":"Song"},{"key":"ref18","article-title":"Meta-adapter: An online few-shot learner for vision-language model","volume-title":"Proc. NeurIPS","author":"Cheng"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273455"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref22","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216198"},{"key":"ref26","first-page":"9125","article-title":"DetCLIP: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume-title":"Proc. NeurIPS","author":"Yao"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00583"},{"key":"ref28","article-title":"CoDet: Co-occurrence guided region-word alignment for open-vocabulary object detection","volume-title":"Proc. NeurIPS","author":"Ma"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref32","article-title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","volume-title":"Proc. ICLR","author":"Zhou"},{"key":"ref33","article-title":"SCLIP: Rethinking self-attention for dense vision-language inference","author":"Wang","year":"2023","journal-title":"arXiv:2312.01597"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290469"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3217720"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3315555"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2861573"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3265051"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333528"},{"key":"ref44","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00274"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"ref49","first-page":"3122","article-title":"Unsupervised template learning for fine-grained object recognition","volume-title":"Proc. NeurIPS","volume":"25","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.128"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.206"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref53","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref54","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612403"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","article-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref62","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"1","key":"ref67","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop","volume":"2","author":"Khosla"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref69","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ouyang"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref72","article-title":"A hard-to-beat baseline for training-free CLIP-based adaptation","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32534"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02336"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11031126.pdf?arnumber=11031126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:18:05Z","timestamp":1755627485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11031126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3573498","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}