{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T09:05:36Z","timestamp":1784365536630,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2021QY2102"],"award-info":[{"award-number":["2021QY2102"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172089"],"award-info":[{"award-number":["62172089"]}],"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":["61972087"],"award-info":[{"award-number":["61972087"]}],"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":["62172090"],"award-info":[{"award-number":["62172090"]}],"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":["62106045"],"award-info":[{"award-number":["62106045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["19@ZH014"],"award-info":[{"award-number":["19@ZH014"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Nanjing Purple Mountain Laboratory"},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20191258"],"award-info":[{"award-number":["BK20191258"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Key Laboratory of Network and Information Security","award":["BM2003201"],"award-info":[{"award-number":["BM2003201"]}]},{"name":"Key Laboratory of Computer Network and Information Integration of Ministry of Education of China","award":["93K-9"],"award-info":[{"award-number":["93K-9"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3408256","type":"journal-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T17:48:25Z","timestamp":1717436905000},"page":"10036-10049","source":"Crossref","is-referenced-by-count":23,"title":["Semantic-Guided Representation Enhancement for Multi-Label Image Classification"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7676-2843","authenticated-orcid":false,"given":"Xuelin","family":"Zhu","sequence":"first","affiliation":[{"name":"Jiangsu Provincial Key Laboratory of Computer Network Technology and the School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8554-6886","authenticated-orcid":false,"given":"Jianshu","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group Company Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2448-6717","authenticated-orcid":false,"given":"Jiuxin","family":"Cao","sequence":"additional","affiliation":[{"name":"Jiangsu Provincial Key Laboratory of Computer Network Technology and the School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6311-2550","authenticated-orcid":false,"given":"Dongqi","family":"Tang","sequence":"additional","affiliation":[{"name":"Ant Group Company Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5323-5343","authenticated-orcid":false,"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group Company Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5209-9063","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2913513"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref5","article-title":"Query2Label: A simple transformer way to multi-label classification","author":"Liu","year":"2021","journal-title":"arXiv:2107.10834"},{"key":"ref6","article-title":"Multi-label image classification with contrastive learning","author":"Dao","year":"2021","journal-title":"arXiv:2107.11626"},{"key":"ref7","article-title":"Hadamard product for low-rank bilinear pooling","author":"Kim","year":"2017","journal-title":"arXiv:1610.04325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.37"},{"issue":"2","key":"ref10","first-page":"1","article-title":"Multi-label image classification with a probabilistic label enhancement model","volume-title":"Proc. UAI","volume":"1","author":"Li"},{"key":"ref11","article-title":"Deep convolutional ranking for multilabel image annotation","author":"Gong","year":"2014","journal-title":"arXiv:1312.4894"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01345"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12230"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref16","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2848458"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083978"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12281"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268997"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3128054"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"ref37","article-title":"MlTr: Multi-label classification with transformer","author":"Cheng","year":"2021","journal-title":"arXiv:2106.06195"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548343"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284812"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288205"},{"key":"ref41","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00142"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"ref45","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2812605"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2612829"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002185"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148867"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.13068"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"ref53","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref54","article-title":"A disciplined approach to neural network hyper-parameters: Part 1\u2014Learning rate, batch size, momentum, and weight decay","author":"Smith","year":"2018","journal-title":"arXiv:1803.09820"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref56","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240567"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00113"},{"key":"ref65","article-title":"Multi-label image recognition with multi-class attentional regions","author":"Gao","year":"2020","journal-title":"arXiv:2007.01755"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475191"},{"key":"ref68","first-page":"18430","article-title":"Label-aware global consistency for multi-label learning with single positive labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xie"},{"issue":"8","key":"ref69","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref70","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10739869\/10546293.pdf?arnumber=10546293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:39:18Z","timestamp":1736368758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10546293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":70,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3408256","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}