{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T22:07:22Z","timestamp":1784412442784,"version":"3.55.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586034","type":"print"},{"value":"9783030586041","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58604-1_7","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T22:02:49Z","timestamp":1604354569000},"page":"104-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":183,"title":["Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments"],"prefix":"10.1007","author":[{"given":"Jacob","family":"Krantz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Wijmans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjun","family":"Majumdar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"7_CR1","unstructured":"Locobot: an open source low cost robot (2019). https:\/\/locobot-website.netlify.com\/"},{"key":"7_CR2","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757 (2018)"},{"key":"7_CR3","unstructured":"Anderson, P., Shrivastava, A., Parikh, D., Batra, D., Lee, S.: Chasing ghosts: instruction following as Bayesian state tracking. In: NeurIPS (2019)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV (2017). MatterPort3D dataset license available at: http:\/\/kaldir.vc.in.tum.de\/matterport\/MP_TOS.pdf","DOI":"10.1109\/3DV.2017.00081"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., Suhr, A., Misra, D., Snavely, N., Artzi, Y.: Touchdown: natural language navigation and spatial reasoning in visual street environments. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01282"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Das, A., Datta, S., Gkioxari, G., Lee, S., Parikh, D., Batra, D.: Embodied question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00008"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7_CR9","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: NeurIPS (2018)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Gordon, D., Kembhavi, A., Rastegari, M., Redmon, J., Fox, D., Farhadi, A.: IQA: visual question answering in interactive environments. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00430"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, S., Davidson, J., Levine, S., Sukthankar, R., Malik, J.: Cognitive mapping and planning for visual navigation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.769"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Hermann, K.M., Malinowski, M., Mirowski, P., Banki-Horvath, A., Anderson, K., Hadsell, R.: Learning to follow directions in street view. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6849"},{"key":"7_CR14","unstructured":"Kadian, A., et al.: Are we making real progress in simulated environments? Measuring the sim2real gap in embodied visual navigation. In: IROS (2020)"},{"key":"7_CR15","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Kohlbrecher, S., Meyer, J., von Stryk, O., Klingauf, U.: A flexible and scalable slam system with full 3D motion estimation. In: SSRR. IEEE, November 2011","DOI":"10.1109\/SSRR.2011.6106777"},{"key":"7_CR17","unstructured":"Ma, C.Y., et al.: Self-monitoring navigation agent via auxiliary progress estimation. In: ICLR (2019)"},{"key":"7_CR18","unstructured":"Magalhaes, G., Jain, V., Ku, A., Ie, E., Baldridge, J.: Effective and general evaluation for instruction conditioned navigation using dynamic time warping. arXiv preprint arXiv:1907.05446 (2019)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: a platform for embodied AI research. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Misra, D., Bennett, A., Blukis, V., Niklasson, E., Shatkhin, M., Artzi, Y.: Mapping instructions to actions in 3D environments with visual goal prediction. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1287"},{"issue":"5","key":"7_CR21","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular slam system. IEEE Trans. Robot. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Robot."},{"key":"7_CR22","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"7_CR24","unstructured":"Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: AISTATS (2011) 3, 10, 12"},{"key":"7_CR25","series-title":"The Springer International Series in Engineering and Computer Science","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/978-1-4615-6325-9_11","volume-title":"Intelligent Unmanned Ground Vehicles","author":"A Stentz","year":"1997","unstructured":"Stentz, A.: Optimal and efficient path planning for partially known environments. In: Hebert, M.H., Thorpe, C., Stentz, A. (eds.) Intelligent Unmanned Ground Vehicles. SECS, vol. 388, pp. 203\u2013220. Springer, Boston (1997). https:\/\/doi.org\/10.1007\/978-1-4615-6325-9_11"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Tan, H., Yu, L., Bansal, M.: Learning to navigate unseen environments: back translation with environmental dropout. In: NAACL HLT (2019)","DOI":"10.18653\/v1\/N19-1268"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Thomason, J., Gordon, D., Bisk, Y.: Shifting the baseline: single modality performance on visual navigation & QA. In: NAACL HLT (2019)","DOI":"10.18653\/v1\/N19-1197"},{"key":"7_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Wijmans, E., et al.: Embodied question answering in photorealistic environments with point cloud perception. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00682"},{"key":"7_CR31","unstructured":"Wijmans, E., et al.: DD-PPO: learning near-perfect pointgoal navigators from 2.5 billion frames. In: ICLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58604-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:09:01Z","timestamp":1730506141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58604-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586034","9783030586041"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58604-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}