{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:22:55Z","timestamp":1768072975469,"version":"3.49.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2021B0101400003"],"award-info":[{"award-number":["2021B0101400003"]}]},{"name":"Hong Kong RGC Research Impact Fund","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}]},{"name":"Hong Kong RGC General Research Fund","award":["152221\/19E"],"award-info":[{"award-number":["152221\/19E"]}]},{"name":"Hong Kong RGC General Research Fund","award":["152203\/20E"],"award-info":[{"award-number":["152203\/20E"]}]},{"name":"Hong Kong RGC General Research Fund","award":["152244\/21E"],"award-info":[{"award-number":["152244\/21E"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872310"],"award-info":[{"award-number":["61872310"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102327"],"award-info":[{"award-number":["62102327"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JCYJ20200109142008673"],"award-info":[{"award-number":["JCYJ20200109142008673"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3222657","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T20:39:39Z","timestamp":1668631179000},"page":"7441-7455","source":"Crossref","is-referenced-by-count":11,"title":["Towards Unbiased Multi-Label Zero-Shot Learning With Pyramid and Semantic Attention"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-9585","authenticated-orcid":false,"given":"Ziming","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0449-4525","authenticated-orcid":false,"given":"Jingcai","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1030-7834","authenticated-orcid":false,"given":"Fushuo","family":"Huo","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.14"},{"key":"ref57","first-page":"265","article-title":"On the algorithmic implementation of multiclass kernel-based vector machines","volume":"2","author":"crammer","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref12","first-page":"1","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"norouzi","year":"0","journal-title":"Proc 2nd Int Conf Learn Representations"},{"key":"ref56","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.220"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.562"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref53","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2991527"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"ref55","first-page":"1","article-title":"FSSD: Feature fusion single shot multibox detector","author":"li","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.473"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.321"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3033124"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139211"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.575"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2861573"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00111"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_44"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2505083"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682869"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.649"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2959433"},{"key":"ref8","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013550"},{"key":"ref9","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","author":"socher","year":"2013","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref4","first-page":"2764","article-title":"WSABIE: Scaling up to large vocabulary image annotation","author":"weston","year":"0","journal-title":"Proc 22nd Int Joint Conf Artif Intell"},{"key":"ref3","first-page":"593","article-title":"Large-scale multi-label learning with missing labels","author":"yu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23528-8_9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3088605"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref33","first-page":"734","article-title":"CornerNet: Detecting objects as paired keypoints","author":"law","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref2","article-title":"Deep convolutional ranking for multilabel image annotation","author":"gong","year":"2013"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref24","first-page":"1","article-title":"Generative multi-label zero-shot learning","author":"gupta","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924511"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.644"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.313"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2984091"},{"key":"ref64","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"0","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref63","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00170"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00880"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"ref28","first-page":"13440","article-title":"Orderless recurrent models for multi-label classification","author":"yazici","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref27","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","first-page":"5419","article-title":"Maximizing subset accuracy with recurrent neural networks in multi-label classification","author":"nam","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref60","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Euro Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09953574.pdf?arnumber=9953574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T20:19:53Z","timestamp":1702325993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9953574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3222657","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}