{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:16:26Z","timestamp":1777655786958,"version":"3.51.4"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["62322212"],"award-info":[{"award-number":["62322212"]}],"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":["62072455"],"award-info":[{"award-number":["62072455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3311646","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:36:07Z","timestamp":1694108167000},"page":"3469-3480","source":"Crossref","is-referenced-by-count":61,"title":["SgVA-CLIP: Semantic-Guided Visual Adapting of Vision-Language Models for Few-Shot Image Classification"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3948-7413","authenticated-orcid":false,"given":"Fang","family":"Peng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9755","authenticated-orcid":false,"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2592-5264","authenticated-orcid":false,"given":"Linhui","family":"Xiao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141886"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139211"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3187556"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3152086"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref9","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref10","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3213208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01435"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6101"},{"key":"ref18","first-page":"7115","article-title":"TapNet: Neural network augmented with task-adaptive projection for few-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref21","article-title":"VT-clip: Enhancing vision-language models with visual-guided texts","author":"Zhang","year":"2021"},{"key":"ref22","article-title":"Masked unsupervised self-training for label-free image classification","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Li","year":"2023"},{"key":"ref23","article-title":"Unsupervised prompt learning for vision-language models","author":"Huang","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref27","article-title":"A new meta-baseline for few-shot learning","author":"Chen","year":"2020"},{"key":"ref28","first-page":"4847","article-title":"Adaptive cross-modal few-shot learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Xing","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00269"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref31","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3236212"},{"key":"ref33","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00146"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103352"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1246"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"ref39","article-title":"Prompting through prototype: A prototype-based prompt learning on pretrained vision-language models","author":"Zhang","year":"2022"},{"key":"ref40","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals","year":"2016"},{"key":"ref41","article-title":"Meta-learning for semi-supervised few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref45","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref51","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/a15050147"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00891"},{"key":"ref56","article-title":"How to adapt your large-scale vision-and-language model","author":"Kim","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00886"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01416"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86340-1_39"},{"key":"ref60","first-page":"121","article-title":"Embedding propagation: Smoother manifold for few-shot classification","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Rodrguez","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8070179"},{"key":"ref62","article-title":"Prompting through prototype: A prototype-based prompt learning on pretrained vision-language models","author":"Zhang","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10243119.pdf?arnumber=10243119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:26:06Z","timestamp":1709339166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3311646","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}