{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T05:52:04Z","timestamp":1750830724210,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585822"},{"type":"electronic","value":"9783030585839"}],"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\/978-3-030-58583-9_33","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"550-565","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Spatial Geometric Reasoning for Room Layout Estimation via Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Liangliang","family":"Ren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyang","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Caicedo, J.C., Lazebnik, S.: Active object localization with deep reinforcement learning. In: ICCV, December 2015","DOI":"10.1109\/ICCV.2015.286"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Choi, W., Pantofaru, C., Savarese, S.: Layout estimation of highly cluttered indoor scenes using geometric and semantic cues. In: ICIAP, pp. 489\u2013499 (2013)","DOI":"10.1007\/978-3-642-41184-7_50"},{"key":"33_CR3","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv preprint arXiv:1412.7062 (2014)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Dasgupta, S., Fang, K., Chen, K., Savarese, S.: Delay: robust spatial layout estimation for cluttered indoor scenes. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.73"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Del Pero, L., Bowdish, J., Fried, D., Kermgard, B., Hartley, E., Barnard, K.: Bayesian geometric modeling of indoor scenes. In: CVPR, pp. 2719\u20132726 (2012)","DOI":"10.1109\/CVPR.2012.6247994"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Del Pero, L., Bowdish, J., Kermgard, B., Hartley, E., Barnard, K.: Understanding Bayesian rooms using composite 3D object models. In: CVPR, pp. 153\u2013160 (2013)","DOI":"10.1109\/CVPR.2013.27"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Flint, A., Murray, D., Reid, I.: Manhattan scene understanding using monocular, stereo, and 3D features. In: ICCV, pp. 2228\u20132235 (2011)","DOI":"10.1109\/ICCV.2011.6126501"},{"key":"33_CR8","unstructured":"Gupta, A., Hebert, M., Kanade, T., Blei, D.M.: Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In: NIPS, pp. 1288\u20131296 (2010)"},{"key":"33_CR9","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, New York (2003)"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: ICCV, pp. 1849\u20131856 (2009)","DOI":"10.1109\/ICCV.2009.5459411"},{"key":"33_CR12","unstructured":"Heess, N., et al.: Emergence of locomotion behaviours in rich environments. arXiv preprint arXiv:1707.02286 (2017)"},{"issue":"1","key":"33_CR13","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s11263-006-0031-y","volume":"75","author":"D Hoiem","year":"2007","unstructured":"Hoiem, D., Efros, A.A., Hebert, M.: Recovering surface layout from an image. Int. J. Comput. Vis. 75(1), 151\u2013172 (2007). https:\/\/doi.org\/10.1007\/s11263-006-0031-y","journal-title":"Int. J. Comput. Vis."},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., Badrinarayanan, V., Malisiewicz, T., Rabinovich, A.: RoomNet: end-to-end room layout estimation. In: ICCV, pp. 4865\u20134874 (2017)","DOI":"10.1109\/ICCV.2017.521"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Lee, D.C., Hebert, M., Kanade, T.: Geometric reasoning for single image structure recovery. In: CVPR, pp. 2136\u20132143 (2009)","DOI":"10.1109\/CVPRW.2009.5206872"},{"key":"33_CR16","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"33_CR17","unstructured":"Liu, C., Schwing, A.G., Kundu, K., Urtasun, R., Fidler, S.: Rent3D: floor-plan priors for monocular layout estimation. In: CVPR, pp. 3413\u20133421 (2015)"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Mallya, A., Lazebnik, S.: Learning informative edge maps for indoor scene layout prediction. In: ICCV, pp. 936\u2013944 (2015)","DOI":"10.1109\/ICCV.2015.113"},{"key":"33_CR20","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"33_CR21","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"key":"33_CR22","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML, pp. 807\u2013814 (2010)"},{"key":"33_CR23","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS Autodiff Workshop (2017)"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Ramalingam, S., Pillai, J.K., Jain, A., Taguchi, Y.: Manhattan junction catalogue for spatial reasoning of indoor scenes. In: CVPR, pp. 3065\u20133072 (2013)","DOI":"10.1109\/CVPR.2013.394"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Rao, Y., Lu, J., Zhou, J.: Attention-aware deep reinforcement learning for video face recognition. In: ICCV, pp. 3931\u20133940 (2017)","DOI":"10.1109\/ICCV.2017.424"},{"key":"33_CR26","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Schwing, A.G., Hazan, T., Pollefeys, M., Urtasun, R.: Efficient structured prediction for 3D indoor scene understanding. In: CVPR, pp. 2815\u20132822 (2012)","DOI":"10.1109\/CVPR.2012.6248006"},{"key":"33_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-642-33783-3_22","volume-title":"Computer Vision \u2013 ECCV 2012","author":"AG Schwing","year":"2012","unstructured":"Schwing, A.G., Urtasun, R.: Efficient exact inference for 3D indoor scene understanding. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 299\u2013313. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_22"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: CVPR, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"33_CR30","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"issue":"4","key":"33_CR32","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1145\/2436256.2436276","volume":"56","author":"H Wang","year":"2013","unstructured":"Wang, H., Gould, S., Roller, D.: Discriminative learning with latent variables for cluttered indoor scene understanding. Commun. ACM 56(4), 92\u201399 (2013)","journal-title":"Commun. ACM"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Yun, S., Choi, J., Yoo, Y., Yun, K., Young Choi, J.: Action-decision networks for visual tracking with deep reinforcement learning. In: CVPR, pp. 2711\u20132720 (2017)","DOI":"10.1109\/CVPR.2017.148"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, J., Kan, C., Schwing, A.G., Urtasun, R.: Estimating the 3D layout of indoor scenes and its clutter from depth sensors. In: ICCV, pp. 1273\u20131280 (2013)","DOI":"10.1109\/ICCV.2013.161"},{"key":"33_CR35","unstructured":"Zhang, Y., Yu, F., Song, S., Xu, P., Seff, A., Xiao, J.: Large-scale scene understanding challenge: room layout estimation (2016)"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, H., Lu, M., Yao, A., Guo, Y., Chen, Y., Zhang, L.: Physics inspired optimization on semantic transfer features: an alternative method for room layout estimation. In: CVPR, pp. 10\u201318 (2017)","DOI":"10.1109\/CVPR.2017.99"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhu, S.C.: Scene parsing by integrating function, geometry and appearance models. In: CVPR, pp. 3119\u20133126 (2013)","DOI":"10.1109\/CVPR.2013.401"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV, pp. 1529\u20131537 (2015)","DOI":"10.1109\/ICCV.2015.179"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Zou, C., Colburn, A., Shan, Q., Hoiem, D.: LayoutNet: reconstructing the 3D room layout from a single RGB image. In: CVPR, pp. 2051\u20132059 (2018)","DOI":"10.1109\/CVPR.2018.00219"}],"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\/978-3-030-58583-9_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:11:21Z","timestamp":1731888681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58583-9_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585822","9783030585839"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58583-9_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"19 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. 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)"}}]}}