{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T20:17:16Z","timestamp":1783196236975,"version":"3.54.6"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["25511104302"],"award-info":[{"award-number":["25511104302"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["25511103300"],"award-info":[{"award-number":["25511103300"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302167"],"award-info":[{"award-number":["62302167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["W2521174"],"award-info":[{"award-number":["W2521174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20343"],"award-info":[{"award-number":["U23A20343"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010097","name":"China Association for Science and Technology","doi-asserted-by":"publisher","award":["YESS20240780"],"award-info":[{"award-number":["YESS20240780"]}],"id":[{"id":"10.13039\/100010097","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113884","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T15:00:26Z","timestamp":1777474826000},"page":"113884","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["From static to adaptive multi-view: Nuanced expert prompt tuning for Fine-Grained Image Retrieval"],"prefix":"10.1016","volume":"179","author":[{"given":"Wenbin","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke-Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyu","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.patcog.2026.113884_b1","doi-asserted-by":"crossref","first-page":"2868","DOI":"10.1109\/TIP.2017.2688133","article-title":"Selective convolutional descriptor aggregation for fine-grained image retrieval","volume":"26","author":"Wei","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113884_b2","series-title":"The caltech-ucsd birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"10.1016\/j.patcog.2026.113884_b3","doi-asserted-by":"crossref","unstructured":"Z. Liu, P. Luo, X. Wang, X. Tang, Deep learning face attributes in the wild, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 3730\u20133738.","DOI":"10.1109\/ICCV.2015.425"},{"key":"10.1016\/j.patcog.2026.113884_b4","doi-asserted-by":"crossref","unstructured":"J. Krause, M. Stark, J. Deng, L. Fei-Fei, 3d Object Representations for Fine-grained Categorization, in: Proceedings of the IEEE International Conference on Computer Vision Workshops, 2013, pp. 554\u2013561.","DOI":"10.1109\/ICCVW.2013.77"},{"key":"10.1016\/j.patcog.2026.113884_b5","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.patcog.2026.113884_b6","doi-asserted-by":"crossref","unstructured":"A. Ermolov, L. Mirvakhabova, V. Khrulkov, N. Sebe, I. Oseledets, Hyperbolic Vision Transformers: Combining Improvements in Metric Learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7409\u20137419.","DOI":"10.1109\/CVPR52688.2022.00726"},{"key":"10.1016\/j.patcog.2026.113884_b7","doi-asserted-by":"crossref","unstructured":"S. Kim, B. Jeong, S. Kwak, Hier: Metric Learning beyond Class Labels via Hierarchical Regularization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19903\u201319912.","DOI":"10.1109\/CVPR52729.2023.01906"},{"key":"10.1016\/j.patcog.2026.113884_b8","doi-asserted-by":"crossref","unstructured":"X. Jiang, H. Tang, R. Yan, J. Tang, Z. Li, Dvf: Advancing robust and accurate fine-grained image retrieval with retrieval guidelines, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 2379\u20132388.","DOI":"10.1145\/3664647.3680763"},{"key":"10.1016\/j.patcog.2026.113884_b9","series-title":"Learning semantic proxies from visual prompts for parameter-efficient fine-tuning in deep metric learning","author":"Ren","year":"2024"},{"key":"10.1016\/j.patcog.2026.113884_b10","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.patcog.2026.113884_b11","doi-asserted-by":"crossref","unstructured":"L. Ren, C. Chen, L. Wang, K. Hua, DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 4353\u20134363.","DOI":"10.1109\/CVPR52734.2025.00411"},{"key":"10.1016\/j.patcog.2026.113884_b12","doi-asserted-by":"crossref","unstructured":"K. Zhou, J. Yang, C.C. Loy, Z. Liu, Conditional Prompt Learning for Vision-Language Models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16816\u201316825.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"10.1016\/j.patcog.2026.113884_b13","series-title":"On the expressiveness of visual prompt experts","author":"Le","year":"2025"},{"key":"10.1016\/j.patcog.2026.113884_b14","doi-asserted-by":"crossref","unstructured":"Y. Lu, J. Liu, Y. Zhang, Y. Liu, X. Tian, Prompt distribution learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5206\u20135215.","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"10.1016\/j.patcog.2026.113884_b15","series-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"10.1016\/j.patcog.2026.113884_b16","doi-asserted-by":"crossref","unstructured":"W. Ge, Deep metric learning with hierarchical triplet loss, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 269\u2013285.","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"10.1016\/j.patcog.2026.113884_b17","doi-asserted-by":"crossref","unstructured":"M.U. Khattak, S.T. Wasim, M. Naseer, S. Khan, M.-H. Yang, F.S. Khan, Self-regulating prompts: Foundational model adaptation without forgetting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 15190\u201315200.","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"10.1016\/j.patcog.2026.113884_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113348","article-title":"Classify fine-grained images in hyperbolic space","author":"Yu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113884_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109979","article-title":"A vision transformer for fine-grained classification by reducing noise and enhancing discriminative information","volume":"145","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113884_b20","series-title":"Rethinking vision transformer for large-scale fine-grained image retrieval","author":"Jiang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113884_b21","series-title":"Language-driven fine-grained retrieval","author":"Wang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113884_b22","doi-asserted-by":"crossref","unstructured":"J. He, J.-N. Chen, S. Liu, A. Kortylewski, C. Yang, Y. Bai, C. Wang, Transfg: A transformer architecture for fine-grained recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 2022, pp. 852\u2013860, 1.","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"10.1016\/j.patcog.2026.113884_b23","doi-asserted-by":"crossref","unstructured":"Z. Yang, T. Luo, D. Wang, Z. Hu, J. Gao, L. Wang, Learning to navigate for fine-grained classification, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 420\u2013435.","DOI":"10.1007\/978-3-030-01264-9_26"},{"issue":"2","key":"10.1016\/j.patcog.2026.113884_b24","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/s10462-012-9338-y","article-title":"Mixture of experts: a literature survey","volume":"42","author":"Masoudnia","year":"2014","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.patcog.2026.113884_b25","doi-asserted-by":"crossref","unstructured":"X. Xiao, Y. Zhang, X. Li, T. Wang, X. Wang, Y. Wei, J. Hamm, M. Xu, Visual instance-aware prompt tuning, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 2880\u20132889.","DOI":"10.1145\/3746027.3754858"},{"key":"10.1016\/j.patcog.2026.113884_b26","series-title":"Dual prompt learning for adapting vision-language models to downstream image-text retrieval","author":"Wang","year":"2025"},{"issue":"7","key":"10.1016\/j.patcog.2026.113884_b27","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-024-40004-w","article-title":"A review on multi-view learning","volume":"19","author":"Yu","year":"2025","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.patcog.2026.113884_b28","doi-asserted-by":"crossref","unstructured":"C.-F.R. Chen, Q. Fan, R. Panda, Crossvit: Cross-attention multi-scale vision transformer for image classification, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 357\u2013366.","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"10.1016\/j.patcog.2026.113884_b29","doi-asserted-by":"crossref","unstructured":"W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, L. Shao, Pyramid vision transformer: A versatile backbone for dense prediction without convolutions, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 568\u2013578.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10.1016\/j.patcog.2026.113884_b30","series-title":"CoTMR: Chain-of-thought multi-scale reasoning for training-free zero-shot composed image retrieval","author":"Sun","year":"2025"},{"key":"10.1016\/j.patcog.2026.113884_b31","article-title":"FG-MoE: Heterogeneous mixture of experts model for fine-grained visual classification","author":"Yang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113884_b32","series-title":"Understanding straight-through estimator in training activation quantized neural nets","author":"Yin","year":"2019"},{"issue":"1","key":"10.1016\/j.patcog.2026.113884_b33","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"10.1016\/j.patcog.2026.113884_b34","doi-asserted-by":"crossref","unstructured":"S. Kim, D. Kim, M. Cho, S. Kwak, Proxy Anchor Loss for Deep Metric Learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3238\u20133247.","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"10.1016\/j.patcog.2026.113884_b35","doi-asserted-by":"crossref","unstructured":"H. Oh Song, Y. Xiang, S. Jegelka, S. Savarese, Deep Metric Learning via Lifted Structured Feature Embedding, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4004\u20134012.","DOI":"10.1109\/CVPR.2016.434"},{"key":"10.1016\/j.patcog.2026.113884_b36","series-title":"Imagenet-21k pretraining for the masses","author":"Ridnik","year":"2021"},{"key":"10.1016\/j.patcog.2026.113884_b37","doi-asserted-by":"crossref","unstructured":"X. Wang, H. Zhang, W. Huang, M.R. Scott, Cross-batch memory for embedding learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 6388\u20136397.","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"10.1016\/j.patcog.2026.113884_b38","doi-asserted-by":"crossref","unstructured":"X. Wang, X. Han, W. Huang, D. Dong, M.R. Scott, Multi-similarity Loss with General Pair Weighting for Deep Metric Learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5022\u20135030.","DOI":"10.1109\/CVPR.2019.00516"},{"key":"10.1016\/j.patcog.2026.113884_b39","doi-asserted-by":"crossref","unstructured":"Q. Qian, L. Shang, B. Sun, J. Hu, H. Li, R. Jin, Softtriple Loss: Deep Metric Learning without Triplet Sampling, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6450\u20136458.","DOI":"10.1109\/ICCV.2019.00655"},{"key":"10.1016\/j.patcog.2026.113884_b40","series-title":"Classification is a strong baseline for deep metric learning","author":"Zhai","year":"2018"},{"key":"10.1016\/j.patcog.2026.113884_b41","series-title":"European Conference on Computer Vision","article-title":"Proxynca++: Revisiting and revitalizing proxy neighborhood component analysis","author":"Teh","year":"2020"},{"key":"10.1016\/j.patcog.2026.113884_b42","series-title":"Training vision transformers for image retrieval","author":"El-Nouby","year":"2021"},{"issue":"9","key":"10.1016\/j.patcog.2026.113884_b43","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."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008496?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008496?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T19:43:17Z","timestamp":1783194197000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326008496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":43,"alternative-id":["S0031320326008496"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113884","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From static to adaptive multi-view: Nuanced expert prompt tuning for Fine-Grained Image Retrieval","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113884","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113884"}}