{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T20:05:36Z","timestamp":1785701136796,"version":"3.56.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF OAC","doi-asserted-by":"publisher","award":["2118240,2112606"],"award-info":[{"award-number":["2118240,2112606"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.01504","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T19:56:41Z","timestamp":1664308601000},"page":"15461-15470","source":"Crossref","is-referenced-by-count":19,"title":["One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones"],"prefix":"10.1109","author":[{"given":"Chan Hee","family":"Song","sequence":"first","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihyung","family":"Kil","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai-Yu","family":"Pan","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian M.","family":"Sadler","sequence":"additional","affiliation":[{"name":"U.S. Army Research Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Lun","family":"Chao","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Su","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref33","article-title":"Embodied bert: A transformer model for embodied, language-guided visual task completion","author":"suglia","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref32","author":"souza","year":"2019","journal-title":"Portuguese named entity recognition using BERT-CRF"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00190"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref37","article-title":"Active visual information gathering for vision-language navigation","author":"wang","year":"2020","journal-title":"ECCV"},{"key":"ref36","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"NeurIPS"},{"key":"ref35","article-title":"Attention is all you need","author":"ashish","year":"2017","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.62"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"ref12","article-title":"A recurrent vision-and-language bert for navigation","author":"hong","year":"2021","journal-title":"CVPR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref15","article-title":"Agent with the big picture: Perceiving surroundings for interactive instruction following","author":"kim","year":"0","journal-title":"Embodied AI Workshop CVPR"},{"key":"ref16","article-title":"Generative language-grounded policy in vision-and-language navigation with bayes' rule","author":"kurita","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref18","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref4","article-title":"Embodied question answering","author":"das","year":"2018","journal-title":"CVPR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref5","article-title":"Neural modular control for embodied question answering","author":"das","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.29007\/l6qh"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref2","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","author":"blukis","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref20","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"ma","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Improving vision-and-language navigation with image-text pairs from the web","author":"majumdar","year":"2020","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.368"},{"key":"ref24","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.119"},{"key":"ref23","article-title":"Film: Following instructions in language with modular methods","author":"min","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.60"},{"key":"ref26","article-title":"Modular framework for visuomotor language grounding","author":"kolby","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/128"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"New Orleans, LA, USA","start":{"date-parts":[[2022,6,18]]},"end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09879302.pdf?arnumber=9879302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T20:57:36Z","timestamp":1665781056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9879302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.01504","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}