{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:16:36Z","timestamp":1774124196408,"version":"3.50.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585228","type":"print"},{"value":"9783030585235","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\/978-3-030-58523-5_30","type":"book-chapter","created":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T20:13:16Z","timestamp":1607026396000},"page":"513-529","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation"],"prefix":"10.1007","author":[{"given":"Medhini","family":"Narasimhan","sequence":"first","affiliation":[]},{"given":"Erik","family":"Wijmans","sequence":"additional","affiliation":[]},{"given":"Xinlei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[]},{"given":"Amanpreet","family":"Singh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,12,4]]},"reference":[{"key":"30_CR1","unstructured":"Anderson, P., et al.: On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757 (2018)"},{"key":"30_CR2","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":"30_CR3","unstructured":"Aydemir, A., G\u00f6belbecker, M., Pronobis, A., Sj\u00f6\u00f6, K., Jensfelt, P.: Plan-based object search and exploration using semantic spatial knowledge in the real world. In: ECMR (2011)"},{"key":"30_CR4","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/MRA.2006.1678144","volume":"13","author":"T Bailey","year":"2006","unstructured":"Bailey, T., Durrant-Whyte, H.: Simultaneous localization and mapping (SLAM) Part ii. IEEE Robot. Autom. Mag. 13, 99\u2013110 (2006)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"30_CR5","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. In: Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Bowman, S.L., Atanasov, N., Daniilidis, K., Pappas, G.J.: Probabilistic data association for semantic slam. In: International Conference on Robotics and Automation (ICRA) (2017)","DOI":"10.1109\/ICRA.2017.7989203"},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena, C., et al.: Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans. Robot. 32, 1309\u20131332 (2016)","journal-title":"IEEE Trans. Robot."},{"issue":"2","key":"30_CR8","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s10846-013-9981-9","volume":"75","author":"L Carlone","year":"2013","unstructured":"Carlone, L., Du, J., Kaouk Ng, M., Bona, B., Indri, M.: Active SLAM and exploration with particle filters using Kullback-Leibler divergence. J. Intell. Robot. Syst. 75(2), 291\u2013311 (2013). https:\/\/doi.org\/10.1007\/s10846-013-9981-9","journal-title":"J. Intell. Robot. Syst."},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: Learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017). matterport3D dataset available at https:\/\/niessner.github.io\/Matterport\/","DOI":"10.1109\/3DV.2017.00081"},{"key":"30_CR10","unstructured":"Chen, T., Gupta, S., Gupta, A.: Learning exploration policies for navigation. arXiv preprint arXiv:1903.01959 (2019)"},{"key":"30_CR11","doi-asserted-by":"publisher","first-page":"497","DOI":"10.3390\/app10020497","volume":"10","author":"J Crespo","year":"2020","unstructured":"Crespo, J., Castillo, J.C., Mozos, O.M., Barber, R.: Semantic information for robot navigation: a survey. Appl. Sci. 10, 497 (2020)","journal-title":"Appl. Sci."},{"key":"30_CR12","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"30_CR13","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/MRA.2006.1638022","volume":"13","author":"H Durrant-Whyte","year":"2006","unstructured":"Durrant-Whyte, H., Bailey, T.: Simultaneous localization and mapping: part i. IEEE Robot. Autom. Mag. 13, 99\u2013110 (2006)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Fang, K., Toshev, A., Fei-Fei, L., Savarese, S.: Scene memory transformer for embodied agents in long-horizon tasks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00063"},{"key":"30_CR15","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"issue":"1","key":"30_CR16","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s10462-012-9365-8","volume":"43","author":"J Fuentes-Pacheco","year":"2012","unstructured":"Fuentes-Pacheco, J., Ruiz-Ascencio, J., Rend\u00f3n-Mancha, J.M.: Visual simultaneous localization and mapping: a survey. Artif. Intell. Rev. 43(1), 55\u201381 (2012). https:\/\/doi.org\/10.1007\/s10462-012-9365-8","journal-title":"Artif. Intell. Rev."},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Gupta, S., Davidson, J., Levine, S., Sukthankar, R., Malik, J.: Cognitive mapping and planning for visual navigation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.769"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Hartley, R., Zisserman, A.: Multiple view geometry in computer vision (2003)","DOI":"10.1017\/CBO9780511811685"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"30_CR21","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"30_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"30_CR23","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1177\/0278364907087426","volume":"27","author":"T Kollar","year":"2008","unstructured":"Kollar, T., Roy, N.: Trajectory optimization using reinforcement learning for map exploration. Int. J. Robot. Res. 27, 175\u2013196 (2008)","journal-title":"Int. J. Robot. Res."},{"issue":"1","key":"30_CR24","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017). https:\/\/doi.org\/10.1007\/s11263-016-0981-7","journal-title":"Int. J. Comput. Vis."},{"key":"30_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877","volume-title":"Planning Algorithms","author":"SM LaValle","year":"2006","unstructured":"LaValle, S.M.: Planning Algorithms. Cambridge University Press, Cambridge (2006)"},{"key":"30_CR26","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"30_CR27","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s10514-009-9130-2","volume":"27","author":"R Martinez-Cantin","year":"2009","unstructured":"Martinez-Cantin, R., de Freitas, N., Brochu, E., Castellanos, J., Doucet, A.: A Bayesian exploration-exploitation approach for optimal online sensing and planning with a visually guided mobile robot. Auton. Robots 27, 93\u2013103 (2009). https:\/\/doi.org\/10.1007\/s10514-009-9130-2","journal-title":"Auton. Robots"},{"key":"30_CR28","unstructured":"Mirowski, P., et al.: Learning to navigate in complex environments. arXiv preprint arXiv:1611.03673 (2016)"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Pronobis, A., Jensfelt, P.: Large-scale semantic mapping and reasoning with heterogeneous modalities. In: International Conference on Robotics and Automation (ICRA) (2012)","DOI":"10.1109\/ICRA.2012.6224637"},{"key":"30_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"30_CR31","unstructured":"Savinov, N., Dosovitskiy, A., Koltun, V.: Semi-parametric topological memory for navigation. arXiv preprint arXiv:1803.00653 (2018)"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: A platform for embodied AI research. arXiv preprint arXiv:1904.01201 (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"30_CR33","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"30_CR34","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Stachniss, C., Grisetti, G., Burgard, W.: Information gain-based exploration using Rao-Blackwellized particle filters. In: Robotics: Science and Systems (2005)","DOI":"10.15607\/RSS.2005.I.009"},{"key":"30_CR36","volume-title":"Probabilistic Robotics","author":"S Thrun","year":"2005","unstructured":"Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics. MIT Press, Cambridge (2005)"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Walter, M.R., Hemachandra, S., Homberg, B., Tellex, S., Teller, S.: Learning semantic maps from natural language descriptions. In: Robotics: Science and Systems (2013)","DOI":"10.15607\/RSS.2013.IX.004"},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00679"},{"key":"30_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-030-01270-0_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Xiong, W., Wang, H., Wang, W.Y.: Look before you leap: bridging model-free and model-based reinforcement learning for planned-ahead vision-and-language navigation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 38\u201355. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_3"},{"key":"30_CR40","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.3390\/rs11111363","volume":"11","author":"Z Wang","year":"2019","unstructured":"Wang, Z., Zhang, Q., Li, J., Zhang, S., Liu, J.: A computationally efficient semantic SLAM solution for dynamic scenes. Remote Sens. 11, 1363 (2019)","journal-title":"Remote Sens."},{"key":"30_CR41","unstructured":"Wijmans, E., et al.: DD-PPO: learning near-perfect pointgoal navigators from 2.5 billion frames. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"30_CR42","unstructured":"Wu, Y., Wu, Y., Gkioxari, G., Tian, Y.: Building generalizable agents with a realistic and rich 3D environment. arXiv preprint arXiv:1801.02209 (2018)"},{"key":"30_CR43","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wu, Y., Tamar, A., Russell, S., Gkioxari, G., Tian, Y.: Bayesian relational memory for semantic visual navigation. arXiv preprint arXiv:1909.04306 (2019)","DOI":"10.1109\/ICCV.2019.00286"},{"key":"30_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Wu","year":"2018","unstructured":"Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_1"},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"30_CR46","unstructured":"Yang, W., Wang, X., Farhadi, A., Gupta, A., Mottaghi, R.: Visual semantic navigation using scene priors. arXiv preprint arXiv:1810.06543 (2018)"},{"key":"30_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: International Conference on Robotics and Automation (ICRA) (2017)","DOI":"10.1109\/ICRA.2017.7989381"}],"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\/978-3-030-58523-5_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:12:28Z","timestamp":1733184748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58523-5_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585228","9783030585235"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58523-5_30","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":"4 December 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. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}