{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T11:11:53Z","timestamp":1773918713416,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["20H04269"],"award-info":[{"award-number":["20H04269"]}]},{"name":"JST CREST"},{"name":"JST Moonshot R&D","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]},{"DOI":"10.13039\/501100003051","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/lra.2021.3092686","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:08:21Z","timestamp":1624914501000},"page":"6258-6265","source":"Crossref","is-referenced-by-count":16,"title":["CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0895-5982","authenticated-orcid":false,"given":"Aly","family":"Magassouba","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0261-0510","authenticated-orcid":false,"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","first-page":"382","article-title":"SPICE: Semantic Propositional Image Caption Evaluation","author":"anderson","year":"0","journal-title":"Proc ECCV"},{"key":"ref31","article-title":"Language-guided navigation via cross-modal grounding and alternate adversarial learning","author":"zhang","year":"2020","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.eacl-main.111","article-title":"On the evaluation of vision-and-language navigation instructions","author":"zhao","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref34","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Text Summarization Branches Out"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref11","first-page":"259","article-title":"Toward understanding natural language directions","author":"kollar","year":"0","journal-title":"Proc ACM\/IEEE HRI"},{"key":"ref12","first-page":"2","article-title":"Understanding natural language commands for robotic navigation and mobile manipulation","author":"tellex","year":"0","journal-title":"Proc AAAI Conf Artifi Intell"},{"key":"ref13","first-page":"4906","article-title":"Deep compositional robotic planners that follow natural language commands","author":"kuo","year":"0","journal-title":"Proc ICRA"},{"key":"ref14","article-title":"Trends in integration of vision and language research: A survey of tasks, datasets, and methods","author":"mogadala","year":"2019","journal-title":"J Artif Intell Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref17","first-page":"4000","article-title":"Take the scenic route: Improving generalization in vision-and-language navigation","author":"yu","year":"0","journal-title":"Proc IEEE CVPR Workshop"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref19","article-title":"Improving vision-and-language navigation with image-text pairs from the web","author":"majumdar","year":"0","journal-title":"Proc European Conf Comput Vis (ECCV)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref29","first-page":"630","article-title":"Identity Mappings in Deep Residual Networks","author":"he","year":"0","journal-title":"Proc ECCV"},{"key":"ref5","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"NeurIPS"},{"key":"ref8","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North American Ch Assoc Computat Linguist Human Lang Technol Volume 1 (Long and Short Papers)"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2849607"},{"key":"ref9","first-page":"130 63","article-title":"Unified language model pre-training for natural language understanding and generation","author":"dong","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.08.002"},{"key":"ref20","first-page":"13 137","article-title":"Towards learning a generic agent for vision-and-language navigation via pre-training","author":"hao","year":"0","journal-title":"Proceedings IEEE CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref21","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"wang","year":"2020","journal-title":"Adv Neural Info Proc Syst"},{"key":"ref24","first-page":"104","article-title":"Uniter: Universal Image-Text Representation Learning","author":"chen","year":"0","journal-title":"Proc ECCV"},{"key":"ref23","article-title":"Perceive, transform, and act: Multi-modal attention networks for vision-and-language navigation","author":"landi","year":"2019"},{"key":"ref26","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref25","article-title":"Improving Language Understanding by Generative Pre-Training","author":"radford","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9475905\/09465670.pdf?arnumber=9465670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:08Z","timestamp":1652194448000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9465670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":35,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3092686","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}