{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T07:48:29Z","timestamp":1782287309266,"version":"3.54.5"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114285","type":"journal-article","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T15:03:49Z","timestamp":1781967829000},"page":"114285","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["CacheFL: Federated cache tuning for contrastive vision-language models under limited resources and data"],"prefix":"10.1016","volume":"180","author":[{"given":"Mengjun","family":"Yi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Dou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7285-326X","authenticated-orcid":false,"given":"Furao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.patcog.2026.114285_b1","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: A survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114285_b2","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.114285_b3","first-page":"56959","article-title":"Advancing compositional awareness in clip with efficient fine-tuning","volume":"38","author":"Peleg","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.patcog.2026.114285_b4","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","article-title":"Edge intelligence: Paving the last mile of artificial intelligence with edge computing","volume":"107","author":"Zhou","year":"2019","journal-title":"Proc. IEEE"},{"issue":"1\u20132","key":"10.1016\/j.patcog.2026.114285_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000083","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends Mach. Learn."},{"issue":"17","key":"10.1016\/j.patcog.2026.114285_b6","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2024789118","article-title":"Communication-efficient federated learning","volume":"118","author":"Chen","year":"2021","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.patcog.2026.114285_b7","series-title":"International Conference on Data Engineering","first-page":"965","article-title":"Federated learning on non-iid data silos: An experimental study","author":"Li","year":"2022"},{"issue":"1","key":"10.1016\/j.patcog.2026.114285_b8","first-page":"52","article-title":"Fedclip: Fast generalization and personalization for clip in federated learning","volume":"46","author":"Lu","year":"2023","journal-title":"IEEE Data Eng. Bull."},{"key":"10.1016\/j.patcog.2026.114285_b9","doi-asserted-by":"crossref","unstructured":"M. Zanella, I. Ben Ayed, Low-rank few-shot adaptation of vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 1593\u20131603.","DOI":"10.1109\/CVPRW63382.2024.00166"},{"issue":"05","key":"10.1016\/j.patcog.2026.114285_b10","doi-asserted-by":"crossref","first-page":"5179","DOI":"10.1109\/TMC.2023.3302410","article-title":"PromptFL: Let federated participants cooperatively learn prompts instead of models\u2013federated learning in age of foundation model","volume":"23","author":"Guo","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.patcog.2026.114285_b11","series-title":"European Conference on Computer Vision","first-page":"493","article-title":"Tip-adapter: Training-free adaption of clip for few-shot classification","author":"Zhang","year":"2022"},{"issue":"9","key":"10.1016\/j.patcog.2026.114285_b12","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."},{"issue":"3","key":"10.1016\/j.patcog.2026.114285_b13","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","article-title":"Parameter-efficient fine-tuning of large-scale pre-trained language models","volume":"5","author":"Ding","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114285_b14","doi-asserted-by":"crossref","unstructured":"Y.-L. Sung, J. Cho, M. Bansal, Vl-adapter: Parameter-efficient transfer learning for vision-and-language tasks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5227\u20135237.","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"10.1016\/j.patcog.2026.114285_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106414","article-title":"Hydra: Multi-head low-rank adaptation for parameter efficient fine-tuning","volume":"178","author":"Kim","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.114285_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111460","article-title":"Prompt-ladder: Memory-efficient prompt tuning for vision-language models on edge devices","volume":"163","author":"Cai","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114285_b17","series-title":"International Conference on Learning Representations","first-page":"86715","article-title":"Local-prompt: Extensible local prompts for few-shot out-of-distribution detection","volume":"vol. 2025","author":"Zeng","year":"2025"},{"key":"10.1016\/j.patcog.2026.114285_b18","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"17449","article-title":"Enhance vision-language alignment with noise","volume":"vol. 39","author":"Huang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114285_b19","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"29150","article-title":"Explore how to inject beneficial noise in mllms","volume":"vol. 40","author":"Zhu","year":"2026"},{"key":"10.1016\/j.patcog.2026.114285_b20","series-title":"Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.patcog.2026.114285_b21","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114285_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113774","article-title":"Exploring personalized federated learning from a distribution-based perspective","author":"Yu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114285_b23","first-page":"76018","article-title":"Adaptive lora experts allocation and selection for federated fine-tuning","volume":"38","author":"Wang","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114285_b24","series-title":"International Conference on Machine Learning","first-page":"41473","article-title":"Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes","author":"Qin","year":"2024"},{"key":"10.1016\/j.patcog.2026.114285_b25","doi-asserted-by":"crossref","unstructured":"H. Li, W. Huang, J. Wang, Y. Shi, Global and local prompts cooperation via optimal transport for federated learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 12151\u201312161.","DOI":"10.1109\/CVPR52733.2024.01155"},{"key":"10.1016\/j.patcog.2026.114285_b26","doi-asserted-by":"crossref","unstructured":"F. Zhu, X.-Y. Zhang, C. Wang, F. Yin, C.-L. Liu, Prototype augmentation and self-supervision for incremental learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5871\u20135880.","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"10.1016\/j.patcog.2026.114285_b27","series-title":"International Joint Conference on Neural Networks","first-page":"1","article-title":"Catastrophic forgetting and mode collapse in GANs","author":"Thanh-Tung","year":"2020"},{"key":"10.1016\/j.patcog.2026.114285_b28","unstructured":"X. Li, K. Huang, W. Yang, S. Wang, Z. Zhang, On the Convergence of FedAvg on Non-IID Data, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.patcog.2026.114285_b29","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.patcog.2026.114285_b30","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","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.patcog.2026.114285_b31","doi-asserted-by":"crossref","unstructured":"M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, A. Vedaldi, Describing textures in the wild, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 3606\u20133613.","DOI":"10.1109\/CVPR.2014.461"},{"issue":"7","key":"10.1016\/j.patcog.2026.114285_b32","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.patcog.2026.114285_b33","series-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"10.1016\/j.patcog.2026.114285_b34","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"446","article-title":"Food-101\u2013mining discriminative components with random forests","author":"Bossard","year":"2014"},{"key":"10.1016\/j.patcog.2026.114285_b35","series-title":"Proceedings of the Sixth Indian Conference on Computer Vision, Graphics and Image Processing","first-page":"722","article-title":"Automated flower classification over a large number of classes","author":"Nilsback","year":"2008"},{"key":"10.1016\/j.patcog.2026.114285_b36","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3498","article-title":"Cats and dogs","author":"Parkhi","year":"2012"},{"key":"10.1016\/j.patcog.2026.114285_b37","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.2026.114285_b38","series-title":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"3485","article-title":"Sun database: Large-scale scene recognition from abbey to zoo","author":"Xiao","year":"2010"},{"key":"10.1016\/j.patcog.2026.114285_b39","series-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"10.1016\/j.patcog.2026.114285_b40","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012501?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012501?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T07:17:54Z","timestamp":1782285474000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":40,"alternative-id":["S0031320326012501"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114285","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CacheFL: Federated cache tuning for contrastive vision-language models under limited resources and data","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114285","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":"114285"}}