{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:42Z","timestamp":1777888962810,"version":"3.51.4"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172166"],"award-info":[{"award-number":["62172166"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2022A1515011380"],"award-info":[{"award-number":["2022A1515011380"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00184","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1891-1901","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Cross-Modal Prompt Learning for Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Hao","family":"Zheng","sequence":"first","affiliation":[{"name":"South China Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunzhi","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoxin","family":"He","sequence":"additional","affiliation":[{"name":"South China Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Huang","sequence":"additional","affiliation":[{"name":"South China Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237615"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10059-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3141255"},{"key":"ref17","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref24","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106382"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref31","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Towards interpreting visual information processing in vision-language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Neo"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref34","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"International conference on machine learning","author":"Recht"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ANNES.1993.323080"},{"key":"ref39","article-title":"Consistency-guided prompt learning for vision-language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Roy"},{"key":"ref40","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.604"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","article-title":"Learning robust global representations by penalizing local predictive power","volume":"32","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","article-title":"Uni 2 det: Unified and universal framework for prompt-guided multi-dataset 3d detection","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28387"},{"key":"ref47","article-title":"Hpt++: Hierarchically prompting vision-language models with multi-granularity knowledge generation and improved structure modeling","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3354928"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00653"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"ref53","article-title":"Filip: Fine-grained interactive language-image pre-training","volume-title":"International Conference on Learning Representations","author":"Yao"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28568"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362062"},{"key":"ref56","article-title":"Domain generalization with mixstyle","volume-title":"International Conference on Learning Representations","author":"Zhou"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445968.pdf?arnumber=11445968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:44Z","timestamp":1777611824000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00184","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}