{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T16:04:08Z","timestamp":1787069048581,"version":"build-2736575974"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62571559"],"award-info":[{"award-number":["62571559"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Major Key Project of PCL","award":["PCL2025AS209"],"award-info":[{"award-number":["PCL2025AS209"]}]},{"name":"Guangdong Excellent Youth Team Program","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3668670","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:50:03Z","timestamp":1772225403000},"page":"6770-6783","source":"Crossref","is-referenced-by-count":1,"title":["Adaptively Fine-Tuning and Ensembling Vision-Language Model for Few-Shot Image Classification"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5457-1487","authenticated-orcid":false,"given":"Jie","family":"Yan","sequence":"first","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7301-3840","authenticated-orcid":false,"given":"Baishun","family":"Dong","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4027-0219","authenticated-orcid":false,"given":"Xiaoyuan","family":"Guan","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8838-4963","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-0369","authenticated-orcid":false,"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. 37th Int. Conf. Comput. Vis.","author":"Chen","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref3","article-title":"Learning from Few Examples: A summary of approaches to few-shot learning","author":"Parnami","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3582688"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_26"},{"key":"ref7","first-page":"1","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20885"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3395692"},{"key":"ref10","first-page":"1","article-title":"A baseline for few-shot image classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dhillon","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref12","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2022"},{"key":"ref13","first-page":"1","article-title":"CoCa: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Radford","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27950"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292519"},{"key":"ref20","article-title":"AutoAugment: Learning augmentation policies from data","author":"Cubuk","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3366404"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3450124"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27862"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3227574"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142955"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110485"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00526"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6130"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref34","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Jia","year":"2021"},{"key":"ref35","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Li","year":"2022"},{"key":"ref36","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref37","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32576"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10915-y"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521785"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02201"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3311646"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s24113624"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_15"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"ref51","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref52","first-page":"1","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Allen-Zhu","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626396"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref61","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref65","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00005-y"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02244"},{"key":"ref68","first-page":"1","article-title":"A hard-to-beat baseline for training-free CLIP-based adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2024"},{"key":"ref69","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref70","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11417247.pdf?arnumber=11417247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:04:40Z","timestamp":1785870280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3668670","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}