{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T07:24:35Z","timestamp":1770276275003,"version":"3.49.0"},"reference-count":75,"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":"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072112"],"award-info":[{"award-number":["62072112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2020AAA0108301"],"award-info":[{"award-number":["2020AAA0108301"]}]},{"name":"Key Area Support Plan of Guangdong Province for Jihua Laboratory","award":["X190051TB190"],"award-info":[{"award-number":["X190051TB190"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tcsvt.2023.3324648","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T18:31:36Z","timestamp":1697481096000},"page":"3409-3423","source":"Crossref","is-referenced-by-count":9,"title":["A Transferable Generative Framework for Multi-Label Zero-Shot Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6391-7527","authenticated-orcid":false,"given":"Peirong","family":"Ma","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6674-6003","authenticated-orcid":false,"given":"Zhiquan","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8478-0750","authenticated-orcid":false,"given":"Wu","family":"Ran","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4572-2854","authenticated-orcid":false,"given":"Hong","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3206501"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083978"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"ref9","article-title":"Generative multi-label zero-shot learning","author":"Gupta","year":"2021","journal-title":"arXiv:2101.11606"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859828"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00758"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6844"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00859"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208256"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3155602"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239390"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243205"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3147902"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067067"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2984666"},{"key":"ref29","first-page":"433","article-title":"Learning visual attributes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Ferrari"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref34","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Frome"},{"key":"ref35","first-page":"2152","article-title":"An embarrassingly simple approach to zero-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Romera-Paredes"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2408354"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref40","first-page":"1","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gulrajani"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3128054"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00069"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3538708"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0695-z"},{"key":"ref47","article-title":"The Caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref49","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03749-2"},{"key":"ref54","first-page":"1","article-title":"Zero-shot learning by convex combination of semantic embeddings","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Norouzi"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref56","first-page":"1","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kim"},{"key":"ref57","volume-title":"OpenImages: A Public Dataset for Large-Scale Multi-Label and Multi-Class Image Classification","author":"Krasin","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6868"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_10"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.696"},{"key":"ref62","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1320"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2050"},{"key":"ref65","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mikolov"},{"key":"ref66","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref72","article-title":"Open-vocabulary semantic segmentation with mask-adapted clip","author":"Liang","year":"2022","journal-title":"arXiv:2210.04150"},{"key":"ref73","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","author":"Luo","year":"2022","journal-title":"arXiv:2211.14813"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311618"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10527423\/10286122.pdf?arnumber=10286122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:33:31Z","timestamp":1715362411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10286122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":75,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3324648","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}