{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T12:28:10Z","timestamp":1789129690835,"version":"build-2803163510"},"reference-count":71,"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":["2019B010155002"],"award-info":[{"award-number":["2019B010155002"]}]},{"name":"Peng Cheng Laboratory Research","award":["PCL2021A07"],"award-info":[{"award-number":["PCL2021A07"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102205"],"award-info":[{"award-number":["62102205"]}],"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":["62276195"],"award-info":[{"award-number":["62276195"]}],"id":[{"id":"10.13039\/501100001809","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.2022.3214090","type":"journal-article","created":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T19:40:36Z","timestamp":1665603636000},"page":"6702-6716","source":"Crossref","is-referenced-by-count":9,"title":["Unpaired Image Captioning by Image-Level Weakly-Supervised Visual Concept Recognition"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7678-0005","authenticated-orcid":false,"given":"Peipei","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8135-1659","authenticated-orcid":false,"given":"Zhenglong","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Changwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3060948"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00751"},{"key":"ref59","first-page":"1","article-title":"Looking for a few good metrics: ROUGE and its evaluation","author":"lin","year":"0","journal-title":"Proc 4th NTCIR Workshops"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref53","first-page":"984","article-title":"Indicator function and its application in two-level factorial designs","volume":"31","author":"kenny","year":"2003","journal-title":"Ann Statist"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"ref55","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"andrej","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/128"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00054"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref50","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"komodakis","year":"2017","journal-title":"Int Conf Learn Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref48","first-page":"3915","article-title":"SGM: Sequence generation model for multi-label classification","author":"yang","year":"0","journal-title":"Proc 27th Int Conf Comput Linguistics"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref44","article-title":"Unsupervised machine translation using monolingual corpora only","author":"lample","year":"2018","journal-title":"Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.130"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref8","article-title":"Teaching machines to describe images with natural language feedback","volume":"30","author":"fidler","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2951226"},{"key":"ref37","article-title":"A semi-supervised framework for image captioning","author":"chen","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_37"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2931815"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_31"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1208"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref70","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063377"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.291"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.197"},{"key":"ref26","article-title":"Deconfounded image captioning: A causal retrospect","author":"yang","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.8"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1837885.1837906"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00433"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350996"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref66","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2015","journal-title":"Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref65","first-page":"2085","article-title":"Phrase-based image captioning","author":"lebret","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref27","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref62","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"tolstikhin","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09917391.pdf?arnumber=9917391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T20:22:57Z","timestamp":1702326177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9917391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3214090","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}