{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T21:20:56Z","timestamp":1774646456677,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"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":["61733013"],"award-info":[{"award-number":["61733013"]}],"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":["62173248"],"award-info":[{"award-number":["62173248"]}],"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":["62233013"],"award-info":[{"award-number":["62233013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"name":"Science and Technology Innovation Action Plan-AI Technology Support Project","award":["22511104900"],"award-info":[{"award-number":["22511104900"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","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":[[2023,7]]},"DOI":"10.1109\/tcsvt.2022.3233554","type":"journal-article","created":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T19:00:39Z","timestamp":1672686039000},"page":"3441-3454","source":"Crossref","is-referenced-by-count":26,"title":["RES-StS: Referring Expression Speaker via Self-Training With Scorer for Goal-Oriented Vision-Language Navigation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1368-0300","authenticated-orcid":false,"given":"Liuyi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2166-4450","authenticated-orcid":false,"given":"Zongtao","family":"He","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1176-3735","authenticated-orcid":false,"given":"Ronghao","family":"Dang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1209-461X","authenticated-orcid":false,"given":"Huiyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Art and Design, Rutgers University, New Brunswic, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7543-0855","authenticated-orcid":false,"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5644-1188","authenticated-orcid":false,"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref6","first-page":"1","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref8","first-page":"1","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Fried"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3138129"},{"key":"ref12","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sohn"},{"key":"ref13","first-page":"1","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Berthelot"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref15","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zoph"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2972281"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3122579"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref25","first-page":"1","article-title":"Visual landmark selection for generating grounded and interpretable navigation instructions","volume-title":"Proc. CVPR Workshop Deep Learn. Semantic Vis. Navigat.","author":"Agarwal"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref32","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"Markus Asano","year":"2019","journal-title":"arXiv:1911.05371"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3155746"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3104398"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001684"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3206496"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3210271"},{"key":"ref38","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"Pereyra","year":"2017","journal-title":"arXiv:1701.06548"},{"key":"ref39","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"Xie","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1605"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.111"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref49","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2034"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref55","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019","journal-title":"arXiv:1901.03035"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref60","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref61","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Gehring"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3152990"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10170754\/10004992.pdf?arnumber=10004992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T14:10:24Z","timestamp":1709388624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10004992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":63,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3233554","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}