{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:50:54Z","timestamp":1772905854599,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology","award":["2021ZD0112902"],"award-info":[{"award-number":["2021ZD0112902"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["623B2057"],"award-info":[{"award-number":["623B2057"]}],"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":["62220106003"],"award-info":[{"award-number":["62220106003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Initiative Scientific Research Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3460180","type":"journal-article","created":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T17:58:17Z","timestamp":1726250297000},"page":"11186-11199","source":"Crossref","is-referenced-by-count":4,"title":["Tuning Vision-Language Models With Multiple Prototypes Clustering"],"prefix":"10.1109","volume":"46","author":[{"given":"Meng-Hao","family":"Guo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6545-4672","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9197-346X","authenticated-orcid":false,"given":"Tai-Jiang","family":"Mu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2338-6535","authenticated-orcid":false,"given":"Sharon X.","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7507-6542","authenticated-orcid":false,"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ChatGPT: Optimizing language models for dialogue","year":"2022"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref5","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref15","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref16","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref17","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0382-0"},{"key":"ref19","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref22","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref25","article-title":"CLIPSelf: Vision transformer distills itself for open-vocabulary dense prediction","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3434373"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0393-x"},{"key":"ref29","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548242"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref34","first-page":"5085","article-title":"Transfer learning via learning to transfer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ying"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref38","article-title":"FD-align: Feature discrimination alignment for fine-tuning pre-trained models in few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3265842"},{"key":"ref40","article-title":"In-context learning unlocked for diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref41","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.626"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"ref45","article-title":"GraphAdapter: Tuning vision-language models with dual knowledge graph","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3403155"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00840"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00140"},{"key":"ref52","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01471"},{"key":"ref54","first-page":"38655","article-title":"Text-adaptive multiple visual prototype matching for video-text retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01125"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref57","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"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"},{"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"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref68","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref69","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref70","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3097-4"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref75","article-title":"Eva-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10679902.pdf?arnumber=10679902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T22:44:15Z","timestamp":1732661055000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10679902\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":75,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3460180","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}