{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:31:25Z","timestamp":1781292685501,"version":"3.54.1"},"reference-count":46,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00191","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1968-1978","source":"Crossref","is-referenced-by-count":1,"title":["Language-Driven Multi-Label Zero-Shot Learning with Semantic Granularity"],"prefix":"10.1109","author":[{"given":"Shouwen","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Wan","sequence":"additional","affiliation":[{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junbin","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00073"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.607"},{"key":"ref7","first-page":"16622","article-title":"Hsva: Hierarchical semantic-visual adaptation for zero-shot learning","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_6"},{"key":"ref13","article-title":"De-vise: A deep visual-semantic embedding model","volume":"26","author":"Frome","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01067"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28139"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.83"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01574"},{"key":"ref26","article-title":"Language-driven cross-modal classifier for zero-shot multi-label image recognition","volume-title":"Forty-first International Conference on Machine Learning","author":"Liu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02285"},{"key":"ref28","article-title":"Visual classification via description from large language models","volume-title":"the Eleventh International Conference on Learning Representations","author":"Menon","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"ref30","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"Norouzi","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref31","first-page":"26342","article-title":"Chils: Zero-shot image classification with hierarchical label sets","volume-title":"International Conference on Machine Learning","author":"Novack","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924511"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012782908347"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2216"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00155"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/11527862_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01345"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00023"}],"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\/11445401.pdf?arnumber=11445401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:46Z","timestamp":1777529686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00191","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}