{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:57Z","timestamp":1777865337606,"version":"3.51.4"},"reference-count":37,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFC3805203"],"award-info":[{"award-number":["2023YFC3805203"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402354"],"award-info":[{"award-number":["62402354"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00268","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2793-2802","source":"Crossref","is-referenced-by-count":0,"title":["Learning Visual Proxy for Compositional Zero-Shot Learning"],"prefix":"10.1109","author":[{"given":"Shiyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenchen","family":"Jing","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hainan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547798"},{"key":"ref2","first-page":"1462","article-title":"A causal view of compositional zero-shot recognition","volume":"33","author":"Atzmon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02266"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3487631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00912"},{"key":"ref12","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","author":"Devlin Ming-Wei Chang Kenton"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00522"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01612"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01133"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02256"},{"key":"ref19","article-title":"Drpt: Disentangled and recurrent prompt tuning for compositional zero-shot learning","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00518"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"ref24","article-title":"Learning to compose soft prompts for compositional zero-shot learning","volume-title":"In Proceedings of the International Conference on Learning Representations","author":"Yu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00369"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00369"},{"key":"ref27","first-page":"36","article-title":"Intra-modal proxy learning for zero-shot visual categorization with clip","author":"Qian","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"8","key":"ref28","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref30","first-page":"10641","article-title":"Independent prototype propagation for zero-shot compositionality","volume":"34","author":"Ruis","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01329"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645687"},{"key":"ref34","article-title":"Prompting large pre-trained vision-language models for compositional concept learning","author":"Xu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00567"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.32"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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\/11445243.pdf?arnumber=11445243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:29Z","timestamp":1777529849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445243\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00268","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}