{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:50:04Z","timestamp":1775681404414,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209181","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Determined Multi-Label Learning via Similarity-Based Prompt"],"prefix":"10.1109","author":[{"given":"Meng","family":"Wei","sequence":"first","affiliation":[{"name":"China University of Mining and Technology,School of Computer Science and Technology,Xuzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongnian","family":"Li","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology,School of Computer Science and Technology,Xuzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Ying","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology,School of Computer Science and Technology,Xuzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ridong","family":"Han","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology,School of Computer Science and Technology,Xuzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongfeng","family":"Sun","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology,School of Computer Science and Technology,Xuzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinzheng","family":"Xu","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology,School of Computer Science and Technology,Xuzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6435"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/509"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.12.019"},{"key":"ref4","article-title":"Multi-label prediction via compressed sensing","author":"Hsu","year":"2009","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00099"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01376"},{"key":"ref8","first-page":"21765","article-title":"One positive label is sufficient: Single-positive multi-label learning with label enhancement","volume":"35","author":"Xu","year":"2022","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01849-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658056"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939756"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539466"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467259"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00472"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/415"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.07.030"},{"key":"ref18","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref20","author":"Yu","year":"2022","journal-title":"Coca: Contrastive captioners are image-text foundation models"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00776"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00179"},{"key":"ref25","first-page":"10948","article-title":"Provably consistent partial-label learning","volume":"33","author":"Feng","year":"2020","journal-title":"NeurIPS"},{"key":"ref26","article-title":"The pascal visual object classes challenge 2012 (voc2012) results","volume-title":"VOC\/voc2012\/workshop\/index.html","volume":"2012","author":"Everingham","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref29","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.39"},{"key":"ref31","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209181.pdf?arnumber=11209181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:01:07Z","timestamp":1775678467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209181","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}