{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T21:12:55Z","timestamp":1754601175382,"version":"3.38.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) funded by Korean Government (MSIT) through the Artificial Intelligence Graduate School Program","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}]},{"name":"National Research Foundation of Korea (NRF) funded by Korean Government","award":["NRF-2022R1A4A1030579","NRF-2022M3C1A309202211"],"award-info":[{"award-number":["NRF-2022R1A4A1030579","NRF-2022M3C1A309202211"]}]},{"name":"AI-Bio Research Grant through Seoul National University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3545772","type":"journal-article","created":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T18:51:39Z","timestamp":1740509499000},"page":"36965-36977","source":"Crossref","is-referenced-by-count":1,"title":["Class Concept Representation From Contextual Texts for Training-Free Multi-Label Recognition"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2486-2783","authenticated-orcid":false,"given":"Dong","family":"Un Kang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8679-8742","authenticated-orcid":false,"given":"Hyunwoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8739-8960","authenticated-orcid":false,"given":"Se Young","family":"Chun","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01345"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240567"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929512"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20105"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923552"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2014.110"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00563-8_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3040275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.56578\/mits030104"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.56578\/mits020204"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_29"},{"key":"ref16","article-title":"RPC: A large-scale retail product checkout dataset","author":"Wei","year":"2019","journal-title":"arXiv:1901.07249"},{"key":"ref17","first-page":"30569","article-title":"DualCoOp: Fast adaptation to multi-label recognition with limited annotations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sun"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00472"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00099"},{"key":"ref22","first-page":"21765","article-title":"One positive label is sufficient: Single-positive multi-label learning with label enhancement","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Xu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref26","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Alayrac"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref29","first-page":"14274","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Shu"},{"key":"ref30","first-page":"547","article-title":"A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Allingham"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X99002149"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2277"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1037\/rev0000094"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref35","first-page":"1","article-title":"Visual classification via description from large language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Menon"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102205"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3435003"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01539-x"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01525-3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00130"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"issue":"3","key":"ref45","first-page":"18","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","volume":"2","author":"Krasin","year":"2017","journal-title":"Dataset"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref47","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","year":"2023","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28139"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00068"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00671"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3388094"},{"key":"ref56","article-title":"Beyond sole strength: Customized ensembles for generalized vision-language models","author":"Lu","year":"2023","journal-title":"arXiv:2311.17091"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346405"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10902374.pdf?arnumber=10902374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T06:03:01Z","timestamp":1741068181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10902374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3545772","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}