{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T19:14:17Z","timestamp":1784747657504,"version":"3.55.0"},"reference-count":62,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571559"],"award-info":[{"award-number":["62571559"]}],"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":["PCL2025AS209"],"award-info":[{"award-number":["PCL2025AS209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134512","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:26:44Z","timestamp":1784071604000},"page":"134512","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Mixture of knowledge from multiple pre-trained foundation models for few-shot recognition"],"prefix":"10.1016","volume":"701","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1693-4613","authenticated-orcid":false,"given":"Junxi","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangxing","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-0369","authenticated-orcid":false,"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134512_bib0005","series-title":"ECCV","article-title":"Food-101 - mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.neucom.2026.134512_bib0010","series-title":"NeurIPS","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.neucom.2026.134512_bib0015","series-title":"ICCV","first-page":"9630","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0020","series-title":"ICLR","article-title":"PLOT: prompt learning with optimal transport for vision-language models","author":"Chen","year":"2023"},{"issue":"7","key":"10.1016\/j.neucom.2026.134512_bib0025","doi-asserted-by":"crossref","first-page":"7143","DOI":"10.1109\/TCSVT.2025.3541960","article-title":"DAT: dual-branch adapter-tuning for few-shot recognition","volume":"35","author":"Chen","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134512_bib0030","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134512_bib0035","series-title":"ICCV","first-page":"9620","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0040","series-title":"CVPR","article-title":"Describing textures in the wild","author":"Cimpoi","year":"2014"},{"key":"10.1016\/j.neucom.2026.134512_bib0045","series-title":"CVPR","article-title":"AutoAugment: learning augmentation strategies from data","author":"Cubuk","year":"2019"},{"key":"10.1016\/j.neucom.2026.134512_bib0050","series-title":"CVPR","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neucom.2026.134512_bib0055","series-title":"BigData","first-page":"3","article-title":"A survey on cross-domain few-shot image classification","author":"Deng","year":"2023"},{"key":"10.1016\/j.neucom.2026.134512_bib0060","series-title":"ICLR","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0065","series-title":"CVIU","article-title":"Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories","author":"Fei-Fei","year":"2004"},{"key":"10.1016\/j.neucom.2026.134512_bib0070","series-title":"ICML","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"10.1016\/j.neucom.2026.134512_bib0075","first-page":"1","article-title":"Clip-adapter: better vision-language models with feature adapters","author":"Gao","year":"2023","journal-title":"IJCV"},{"key":"10.1016\/j.neucom.2026.134512_bib0080","series-title":"Meta-Learning Approaches for Few-Shot Learning: A Survey of Recent Advances","author":"Gharoun","year":"2023"},{"key":"10.1016\/j.neucom.2026.134512_bib0085","series-title":"WACV","first-page":"5709","article-title":"Domain aligned CLIP for few-shot classification","author":"Gondal","year":"2024"},{"key":"10.1016\/j.neucom.2026.134512_bib0090","series-title":"CVPR","first-page":"15979","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neucom.2026.134512_bib0095","series-title":"CVPR","first-page":"9726","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.neucom.2026.134512_bib0100","series-title":"CVPR","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134512_bib0105","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.neucom.2026.134512_bib0110","series-title":"ICCV","article-title":"The many faces of robustness: a critical analysis of out-of-distribution generalization","author":"Hendrycks","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0115","series-title":"CVPR","article-title":"Natural adversarial examples","author":"Hendrycks","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128956","article-title":"Meta channel masking for cross-domain few-shot image classification","volume":"620","author":"Hui","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134512_bib0125","series-title":"ICML","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0130","series-title":"ICCV","article-title":"3D object representations for fine-grained categorization","author":"Krause","year":"2013"},{"key":"10.1016\/j.neucom.2026.134512_bib0135","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.neucom.2026.134512_bib0140","series-title":"ECCV","first-page":"264","article-title":"GalLoP: learning global and local prompts for vision-language models","author":"Lafon","year":"2024"},{"key":"10.1016\/j.neucom.2026.134512_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130056","article-title":"Drop inherent biases: multi-level attention calibration for robust cross-domain few-shot classification","volume":"636","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134512_bib0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129688","article-title":"FMVP: fine-grained meta visual prompt enabled domain-specific few-shot classification","volume":"633","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134512_bib0155","series-title":"CVPR","first-page":"27015","article-title":"Descriptor and word soups: overcoming the parameter efficiency accuracy tradeoff for out-of-distribution few-shot learning","author":"Liao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134512_bib0160","series-title":"CVPR","article-title":"Multimodality helps unimodality: cross-modal few-shot learning with multimodal models","author":"Lin","year":"2023"},{"key":"10.1016\/j.neucom.2026.134512_bib0165","series-title":"ICLR","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.neucom.2026.134512_bib0170","author":"Maji"},{"key":"10.1016\/j.neucom.2026.134512_bib0175","series-title":"ECCV","article-title":"SLIP: self-supervision meets language-image pre-training","author":"Mu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134512_bib0180","series-title":"ICVGIP","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"key":"10.1016\/j.neucom.2026.134512_bib0185","series-title":"CVPR","article-title":"Cats and dogs","author":"Parkhi","year":"2012"},{"key":"10.1016\/j.neucom.2026.134512_bib0190","series-title":"ICCV","article-title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","author":"Pratt","year":"2023"},{"issue":"7","key":"10.1016\/j.neucom.2026.134512_bib0195","doi-asserted-by":"crossref","first-page":"7954","DOI":"10.1109\/TPAMI.2026.3669254","article-title":"Spatio-temporal decoupled knowledge compensator for few-shot action recognition","volume":"48","author":"Qu","year":"2025","journal-title":"TPAMI"},{"key":"10.1016\/j.neucom.2026.134512_bib0200","series-title":"ICML","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0205","series-title":"ICML","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.neucom.2026.134512_bib0210","series-title":"ICML","article-title":"Do ImageNet classifiers generalize to ImageNet?","author":"Recht","year":"2019"},{"key":"10.1016\/j.neucom.2026.134512_bib0215","series-title":"AAAI","first-page":"4740","article-title":"Collaborative consortium of foundation models for open-world few-shot learning","author":"Shao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134512_bib0220","series-title":"CVPR","first-page":"28505","article-title":"DeIL: direct-and-inverse CLIP for open-world few-shot learning","author":"Shao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134512_bib0225","series-title":"CVPR","first-page":"23681","article-title":"A closer look at the few-shot adaptation of large vision-language models","author":"Silva-Rodriguez","year":"2024"},{"key":"10.1016\/j.neucom.2026.134512_bib0230","series-title":"NeurIPS","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017"},{"key":"10.1016\/j.neucom.2026.134512_bib0235","author":"Soomro"},{"key":"10.1016\/j.neucom.2026.134512_bib0240","series-title":"NeurIPS","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2026.134512_bib0245","series-title":"NeurIPS","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134512_bib0250","series-title":"CVPR","article-title":"Robust fine-tuning of zero-shot models","author":"Wortsman","year":"2022"},{"key":"10.1016\/j.neucom.2026.134512_bib0255","series-title":"CVPR","article-title":"SUN database: large-scale scene recognition from abbey to zoo","author":"Xiao","year":"2010"},{"key":"10.1016\/j.neucom.2026.134512_bib0260","series-title":"CVPR","article-title":"Joint distribution matters: deep brownian distance covariance for few-shot classification","author":"Xie","year":"2022"},{"key":"10.1016\/j.neucom.2026.134512_bib0265","series-title":"CVPR","article-title":"Task residual for tuning vision-language models","author":"Yu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134512_bib0270","series-title":"ICLR","article-title":"mixup: beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134512_bib0275","series-title":"CVPR","first-page":"15211","article-title":"Prompt, generate, then cache: cascade of foundation models makes strong few-shot learners","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134512_bib0280","series-title":"ECCV","article-title":"Tip-adapter: training-free adaption of CLIP for few-shot classification","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134512_bib0285","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129082","article-title":"An enhanced few-shot text classification approach by integrating topic modeling and prompt-tuning","volume":"617","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134512_bib0290","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129989","article-title":"Few-shot SAR image classification via multiple prototypes ensemble","volume":"635","author":"Zhao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134512_bib0295","series-title":"CVPR","article-title":"Conditional prompt learning for vision-language models","author":"zhou","year":"2022"},{"key":"10.1016\/j.neucom.2026.134512_bib0300","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":"IJCV"},{"key":"10.1016\/j.neucom.2026.134512_bib0305","series-title":"ICCV","article-title":"Prompt-aligned gradient for prompt tuning","author":"Zhu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134512_bib0310","author":"Zhu"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019107?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019107?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T18:55:28Z","timestamp":1784746528000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226019107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":62,"alternative-id":["S0925231226019107"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134512","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mixture of knowledge from multiple pre-trained foundation models for few-shot recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134512","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 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":"134512"}}