{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:59:58Z","timestamp":1783529998239,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2016YFB1001003"],"award-info":[{"award-number":["2016YFB1001003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61901262"],"award-info":[{"award-number":["61901262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U19B2035"],"award-info":[{"award-number":["U19B2035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61527804"],"award-info":[{"award-number":["61527804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61906119"],"award-info":[{"award-number":["61906119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology of Shanghai Municipality","award":["18DZ1112300"],"award-info":[{"award-number":["18DZ1112300"]}]},{"name":"Shanghai Pujiang Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1109\/tcsvt.2020.3039522","type":"journal-article","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T20:49:07Z","timestamp":1605905347000},"page":"3469-3481","source":"Crossref","is-referenced-by-count":60,"title":["Language-Guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3634-2630","authenticated-orcid":false,"given":"Weixia","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-2845","authenticated-orcid":false,"given":"Chao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3631-256X","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref33","first-page":"1564","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref31","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"1","article-title":"Multi-view learning for vision-and-language navigation","volume":"abs 2003 857","author":"qiaolin","year":"2020","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.416"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00729"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref27","first-page":"1","article-title":"On evaluation of embodied navigation agents","volume":"abs 1807 6757","author":"anderson","year":"2018","journal-title":"CoRR"},{"key":"ref29","first-page":"1","article-title":"Improving vision-and-language navigation with image-text pairs from the Web","volume":"asb 2004 14973","author":"arjun","year":"2020","journal-title":"CoRR"},{"key":"ref2","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref20","first-page":"806","article-title":"Learning to follow navigational directions","author":"vogel","year":"2010","journal-title":"Proc Assoc for Computational Linguistics (ACL '01)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref21","first-page":"1","article-title":"Learning to interpret natural language navigation instructions from observations","author":"chen","year":"2011","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref24","first-page":"2054","article-title":"Embodied question answering","author":"das","year":"2018","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref23","first-page":"1","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref26","first-page":"280","article-title":"Videonavqa: Bridging the gap between visual and embodied question answering","author":"c?t?lina","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","first-page":"1","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8482813"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref11","first-page":"10","article-title":"Vision-language navigation with self-supervised auxiliary reasoning tasks","author":"zhu","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref13","first-page":"1","article-title":"End to end learning for self-driving cars","volume":"abs 1604 7316","author":"bojarski","year":"2016","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1426"},{"key":"ref17","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"4601","article-title":"Professor forcing: A new algorithm for training recurrent networks","author":"lamb","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139984"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref3","first-page":"1","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"ma","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1655"},{"key":"ref7","first-page":"1","article-title":"Embodied vision-and-language navigation with dynamic convolutional filters","author":"landi","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00937"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.606"},{"key":"ref42","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"},{"key":"ref44","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proc Int Conf Artif Intell Statist"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9527373\/09265290.pdf?arnumber=9265290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:23Z","timestamp":1652194223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9265290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":56,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.3039522","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9]]}}}