{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T23:20:55Z","timestamp":1778628055899,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore under its AI Singapore Programme","doi-asserted-by":"publisher","award":["AISG-RP-2018-003"],"award-info":[{"award-number":["AISG-RP-2018-003"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MOE AcRF Tier-1 Research","award":["RG95\/20"],"award-info":[{"award-number":["RG95\/20"]}]},{"name":"OPPO Research Grant"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106204"],"award-info":[{"award-number":["62106204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Natural Science Foundation","doi-asserted-by":"publisher","award":["2022NSFSC0911"],"award-info":[{"award-number":["2022NSFSC0911"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Sichuan Natural Science Foundation","doi-asserted-by":"publisher","award":["2022YFG0031"],"award-info":[{"award-number":["2022YFG0031"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for Central Universities of China","doi-asserted-by":"publisher","award":["2682022CX068"],"award-info":[{"award-number":["2682022CX068"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tcsvt.2023.3235704","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:15:11Z","timestamp":1673378111000},"page":"3560-3569","source":"Crossref","is-referenced-by-count":16,"title":["Self-Training Vision Language BERTs With a Unified Conditional Model"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1882-9733","authenticated-orcid":false,"given":"Xiaofeng","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1640-0992","authenticated-orcid":false,"given":"Fengmao","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6649-7660","authenticated-orcid":false,"given":"Fayao","family":"Liu","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-7458","authenticated-orcid":false,"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048440"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2897604"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref37","article-title":"There are many consistent explanations of unlabeled data: Why you should average","author":"athiwaratkun","year":"2018","journal-title":"arXiv 1806 05594"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"},{"key":"ref36","first-page":"1","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"tarvainen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1430"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-32-9748-7_3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref33","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref32","first-page":"1","article-title":"Unified language model pre-training for natural language understanding and generation","volume":"32","author":"dong","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2889922"},{"key":"ref39","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref38","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969330"},{"key":"ref24","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"harold li","year":"2019","journal-title":"arXiv 1908 03557"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref28","article-title":"Billion-scale semi-supervised learning for image classification","author":"yalniz","year":"2019","journal-title":"arXiv 1905 00546"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref29","article-title":"Improving neural machine translation models with monolingual data","author":"sennrich","year":"2015","journal-title":"arXiv 1511 06709"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref9","article-title":"Are we pretraining it right? Digging deeper into visio-linguistic pretraining","author":"singh","year":"2020","journal-title":"arXiv 2004 08744"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref3","article-title":"BERT has a mouth, and it must speak: BERT as a Markov random field language model","author":"wang","year":"2019","journal-title":"arXiv 1902 04094 [cs]"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume":"33","author":"zoph","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10207864\/10013737.pdf?arnumber=10013737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:12:33Z","timestamp":1692641553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10013737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":43,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3235704","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}