{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T01:18:46Z","timestamp":1789607926178,"version":"build-2803163510"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFA1004100"],"award-info":[{"award-number":["2022YFA1004100"]}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DARPA LwLL"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3346405","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T14:51:07Z","timestamp":1703515867000},"page":"3450-3462","source":"Crossref","is-referenced-by-count":34,"title":["DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition With Limited Annotations"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3321-6759","authenticated-orcid":false,"given":"Ping","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2187-0657","authenticated-orcid":false,"given":"Ximeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0711-4313","authenticated-orcid":false,"given":"Stan","family":"Sclaroff","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Boston University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5704-7614","authenticated-orcid":false,"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[{"name":"Boston University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.443"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240567"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01345"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00944"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20105"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref26","first-page":"30569","article-title":"DualCoOp: Fast adaptation to multi-label recognition with limited annotations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref28","article-title":"Unsupervised prompt learning for vision-language models","author":"Huang","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref30","article-title":"Prompt-based multi-modal image segmentation","author":"L\u00fcddecke","year":"2021"},{"key":"ref31","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref33","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01048"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref38","first-page":"712","article-title":"On the optimality of classifier chain for multi-label classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"28","author":"Liu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.320"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2612829"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995734"},{"key":"ref49","first-page":"1274","article-title":"Fast image tagging","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7699"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11644"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3025814"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3295772\/mm1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.313"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924511"},{"key":"ref58","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00780"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref62","article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","author":"Zhang","year":"2021"},{"key":"ref63","article-title":"Variational prompt tuning improves generalization of vision-language models","author":"Derakhshani","year":"2022"},{"key":"ref64","article-title":"Patch-token aligned Bayesian prompt learning for vision-language models","author":"Liu","year":"2023"},{"key":"ref65","article-title":"LoCoOp: Few-shot out-of-distribution detection via prompt learning","author":"Miyai","year":"2023"},{"key":"ref66","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3369699"},{"key":"ref71","article-title":"Visual tuning","author":"Yu","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_33"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2760909"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref81","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"Norouzi","year":"2013"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref83","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.449"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10490207\/10373051-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10373051.pdf?arnumber=10373051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T15:39:23Z","timestamp":1743781163000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10373051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":86,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3346405","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}