{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:59:34Z","timestamp":1780765174468,"version":"3.54.1"},"reference-count":82,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306294"],"award-info":[{"award-number":["62306294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085QF222"],"award-info":[{"award-number":["2308085QF222"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M743385"],"award-info":[{"award-number":["2023M743385"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3432753","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T20:16:38Z","timestamp":1721765798000},"page":"12221-12232","source":"Crossref","is-referenced-by-count":13,"title":["Hierarchy-Aware Interactive Prompt Learning for Few-Shot Classification"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4557-2138","authenticated-orcid":false,"given":"Xiaotian","family":"Yin","sequence":"first","affiliation":[{"name":"Institute of Advanced Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4380-5573","authenticated-orcid":false,"given":"Jiamin","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenfei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sangfor Technologies Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sangfor Technologies Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3315133"},{"key":"ref3","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref4","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv:2107.06383"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref7","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bangalath"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref15","first-page":"31716","article-title":"CLIPood: Generalizing clip to out-of-distributions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02011"},{"key":"ref19","article-title":"Prompt-aligned gradient for prompt tuning","author":"Zhu","year":"2022","journal-title":"arXiv:2205.14865"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01963"},{"key":"ref24","article-title":"From CLIP to DINO: Visual encoders shout in multi-modal large language models","author":"Jiang","year":"2023","journal-title":"arXiv:2310.08825"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099297"},{"key":"ref26","article-title":"CLIPPO: Image-and-language understanding from pixels only","author":"Tschannen","year":"2022","journal-title":"arXiv:2212.08045"},{"key":"ref27","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Information Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref28","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref30","article-title":"RedCaps: Curated image-text data created by the people, for the people","author":"Desai","year":"2021","journal-title":"arXiv:2111.11431"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"ref32","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann"},{"key":"ref33","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref34","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref35","first-page":"1","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sohn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref37","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref38","first-page":"23","article-title":"Task similarity aware meta learning: Theory-inspired improvement on MAML","volume-title":"Proc. Uncertainty Artif. Intell. (UAI)","author":"Zhou"},{"key":"ref39","first-page":"1","article-title":"Efficient meta learning via minibatch proximal update","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhou"},{"key":"ref40","article-title":"Meta-learning with latent embedding optimization","author":"Rusu","year":"2018","journal-title":"arXiv:1807.05960"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00832"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3224003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274168"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248585"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3282777"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232717"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3125129"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2920783"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995754"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263593"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165068"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3188462"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00886"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00702"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3294332"},{"key":"ref60","first-page":"1","article-title":"PLOT: Prompt learning with optimal transport for vision-language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref61","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv:2210.07225"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref65","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref66","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref69","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref78","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref79","first-page":"1","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.08.002"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10606542.pdf?arnumber=10606542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:38:49Z","timestamp":1734982729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10606542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":82,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3432753","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}