{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T10:22:11Z","timestamp":1770718931325,"version":"3.49.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,1,28]],"date-time":"2015-01-28T00:00:00Z","timestamp":1422403200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1007\/s11263-014-0795-4","type":"journal-article","created":{"date-parts":[[2015,1,29]],"date-time":"2015-01-29T18:47:14Z","timestamp":1422557234000},"page":"221-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Scene Understanding by Reasoning Stability and Safety"],"prefix":"10.1007","volume":"112","author":[{"given":"Bo","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Yibiao","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Joey","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Katsushi","family":"Ikeuchi","sequence":"additional","affiliation":[]},{"given":"Song-Chun","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,1,28]]},"reference":[{"key":"795_CR1","unstructured":"Anand, A., Koppula, H., Joachims, T., & Saxena, A. (2012). Contextually guided semantic labeling and search for 3d point clouds. In IJRR."},{"key":"795_CR2","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s00371-006-0375-x","volume":"22","author":"M Attene","year":"2006","unstructured":"Attene, M., Falcidieno, B., & Spagnuolo, M. (2006). Hierarchical mesh segmentation based on fitting primitives. The Visual Computer, 22, 181\u2013193.","journal-title":"The Visual Computer"},{"key":"795_CR3","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1109\/TPAMI.2005.161","volume":"27","author":"A Barbu","year":"2005","unstructured":"Barbu, A., & Zhu, S. C. (2005). Generalizing Swendsen\u2013Wang to sampling arbitrary posterior probabilities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 1239\u20131253.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"795_CR4","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/0010-0285(82)90007-X","volume":"14","author":"I Biederman","year":"1982","unstructured":"Biederman, I., Mezzanotte, R. J., & Rabinowitz, J. C. (1982). Scene perception: Detecting and judging objects undergoing relational violations. Cognitive Psychology, 14(2), 143\u2013177.","journal-title":"Cognitive Psychology"},{"issue":"3","key":"795_CR5","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/34.841760","volume":"22","author":"M Blane","year":"2000","unstructured":"Blane, M., Lei, Z. B., & Cooper, D. B. (2000). The 3L algorithm for fitting implicit polynomial curves and surfaces to data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(3), 298\u2013313.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"795_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Golovinskiy, A., & Funkhouser, T. (2009). A benchmark for 3D mesh segmentation. In SIGGRAPH.","DOI":"10.1145\/1531326.1531379"},{"key":"795_CR7","unstructured":"DARPA. (2014). Robots rescue people. http:\/\/www.i-programmer.info\/news\/169-robotics\/6857-robots-rescue-people.html ."},{"key":"795_CR8","doi-asserted-by":"crossref","unstructured":"Delaitre, V., Fouhey, D., Laptev, I., Sivic, J., Gupta, A., & Efros, A. (2012). Scene semantics from long-term observation of people. In ECCV.","DOI":"10.1007\/978-3-642-33783-3_21"},{"issue":"2","key":"795_CR9","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2), 167\u2013181.","journal-title":"International Journal of Computer Vision"},{"key":"795_CR10","first-page":"109","volume":"39","author":"R Fleming","year":"2010","unstructured":"Fleming, R., Barnett-Cowan, M., & B\u00fclthoff, H. (2010). Perceived object stability is affected by the internal representation of gravity. Perception, 39, 109.","journal-title":"Perception"},{"key":"795_CR11","doi-asserted-by":"crossref","unstructured":"Fouhey, D., Delaitre, V., Gupta, A., Efros, A., Laptev, I., & Sivic, J. (2012). People watching: Human actions as a cue for single-view geometry. In ECCV.","DOI":"10.1007\/978-3-642-33715-4_53"},{"key":"795_CR12","doi-asserted-by":"crossref","unstructured":"Furukawa, Y., Curless, B., Seitz, S. M., & Szeliski, R. (2009). Manhattan-world stereo. In CVPR.","DOI":"10.1109\/CVPR.2009.5206867"},{"key":"795_CR13","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., & Van, G. L. (2011). What makes a chair a chair? In CVPR.","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"795_CR14","doi-asserted-by":"crossref","unstructured":"Guo, R., & Hoiem, D. (2013). Support surface prediction in indoor scenes. In ICCV.","DOI":"10.1109\/ICCV.2013.266"},{"key":"795_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, A., Efros, A., & Hebert, M. (2010). Blocks world revisited: Image understanding using qualitative geometry and mechanics. In ECCV.","DOI":"10.1007\/978-3-642-15561-1_35"},{"key":"795_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Satkin, S., Efros, A., & Hebert, M. (2011). From 3D scene geometry to human workspace. In CVPR.","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"795_CR17","unstructured":"Hamrick, J., Battaglia, P., & Tenenbaum, J. (2011). Internal physics models guide probabilistic judgments about object dynamics. In Proceedings of the 33rd Annual Meeting of the Cognitive Science Society."},{"key":"795_CR18","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., & Forsyth, D. (2010). Thinking inside the box: Using appearance models and context based on room geometry. In ECCV.","DOI":"10.1007\/978-3-642-15567-3_17"},{"key":"795_CR19","doi-asserted-by":"crossref","unstructured":"Janoch, A., Karayev, S., Jia, Y., Barron, J. T., Fritz, M., Saenko, K., & Darrell, T. (2011). A category-level 3-d object dataset: Putting the kinect to work. In ICCV workshop.","DOI":"10.1109\/ICCVW.2011.6130382"},{"key":"795_CR20","doi-asserted-by":"crossref","unstructured":"Jia, Z., Gallagher, A., Saxena, A., & Chen, T. (2013). 3d-based reasoning with blocks, support, and stability. In CVPR.","DOI":"10.1109\/CVPR.2013.8"},{"key":"795_CR21","unstructured":"Jiang, Y., & Saxena, A. (2013). Infinite latent conditional random fields for modeling environments through humans. In Robotics: Science and Systems (RSS)."},{"key":"795_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Koppula, H.S., & Saxena, A. (2013). Hallucinated humans as the hidden context for labeling 3d scenes. In: CVPR.","DOI":"10.1109\/CVPR.2013.385"},{"key":"795_CR23","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Miller, S., & Fei-Fei, L. (2013). Object discovery in 3d scenes via shape analysis. In International Conference on Robotics and Automation (ICRA).","DOI":"10.1109\/ICRA.2013.6630857"},{"key":"795_CR24","unstructured":"Koppula, H., Anand, A., Joachims, T., & Saxena, A. (2011). Semantic labeling of 3d point clouds for indoor scenes. In NIPS."},{"key":"795_CR25","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1177\/027836499701600402","volume":"16","author":"DJ Kriegman","year":"1995","unstructured":"Kriegman, D. J. (1995). Let them fall where they may: Capture regions of curved objects and polyhedra. International Journal of Robotics Research, 16, 448\u2013472.","journal-title":"International Journal of Robotics Research"},{"key":"795_CR26","doi-asserted-by":"crossref","unstructured":"Lee, D., Hebert, M., & Kanade, T. (2009). Geometric reasoning for single image structure recovery. In CVPR.","DOI":"10.1109\/CVPR.2009.5206872"},{"key":"795_CR27","volume-title":"Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces advances in neural information processing systems","author":"D Lee","year":"2010","unstructured":"Lee, D., Gupta, A., Hebert, M., & Kanade, T. (2010). Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces advances in neural information processing systems. Cambridge: MIT."},{"key":"795_CR28","doi-asserted-by":"crossref","unstructured":"McCloskey, M. (1983). Intuitive physics. Scientific American, 248(4), 114\u2013122.","DOI":"10.1038\/scientificamerican0483-122"},{"issue":"6","key":"795_CR29","first-page":"137","volume":"31","author":"L Nan","year":"2012","unstructured":"Nan, L., Xie, K., & Sharf, A. (2012). A search-classify approach for cluttered indoor scene understanding. ACM Transactions on Graphics (TOG), 31(6), 137.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"795_CR30","doi-asserted-by":"crossref","unstructured":"Newcombe, R., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A., Kohli, P., Shotton, J., Hodges, S., & Fitzgibbon, A. (2011). Kinectfusion: Real-time dense surface mapping and tracking. In ISMAR.","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"795_CR31","doi-asserted-by":"crossref","unstructured":"Petti, S., & Fraichard, T. (2005). Safe motion planning in dynamic environments. In IROS.","DOI":"10.1109\/IROS.2005.1545549"},{"key":"795_CR32","doi-asserted-by":"crossref","unstructured":"Phillips, M., & Likhachev, M. (2011). Sipp: Safe interval path planning for dynamic environments. In ICRA.","DOI":"10.1109\/ICRA.2011.5980306"},{"key":"795_CR33","doi-asserted-by":"crossref","unstructured":"Poppinga, J., Vaskevicius, N., Birk, A., & Pathak, K. (2008). Fast plane detection and polygonalization in noisy 3D range images. In IROS.","DOI":"10.1109\/IROS.2008.4650729"},{"key":"795_CR34","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/TPAMI.2005.46","volume":"27","author":"R Sagawa","year":"2005","unstructured":"Sagawa, R., Nishino, K., & Ikeuchi, K. (2005). Adaptively merging large-scale range data with reflectance properties. IEEE Transaction on Pattern Analysis and Machine Intelligence, 27, 392\u2013405.","journal-title":"IEEE Transaction on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"795_CR35","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1145\/2661229.2661230","volume":"33","author":"M Savva","year":"2014","unstructured":"Savva, M., Chang, A. X., Hanrahan, P., & Fisher, M. (2014). Scenegrok: Inferring action maps in 3d environments. ACM Transactions on Graphics (TOG), 33(6), 212.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"795_CR36","first-page":"136","volume":"31","author":"T Shao","year":"2012","unstructured":"Shao, T., Xu, W., Zhou, K., Wang, J., & Li, D. (2012). An interactive approach to semantic modeling of indoor scenes with an rgbd camera. ACM Transactions on Graphics (TOG), 31, 136.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"795_CR37","doi-asserted-by":"crossref","unstructured":"Shao, T., Monszpart, A., Zheng, Y., Koo, B., Ku, W., Zhou, K., et al. (2014). Imagining the unseen: Stability-based cuboid arrangements for scene understanding. ACM Transactions on Graphics (TOG), 33, 209.","DOI":"10.1145\/2661229.2661288"},{"issue":"5","key":"795_CR38","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1109\/TPAMI.1983.4767426","volume":"5","author":"QY Shi","year":"1983","unstructured":"Shi, Q. Y., & Ks, Fu. (1983). Parsing and translation of (attributed) expansive graph languages for scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5(5), 472\u2013485.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"795_CR39","doi-asserted-by":"crossref","unstructured":"Silberman, N., Kohli, P., Hoiem, D. & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. In ECCV.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"795_CR40","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s11263-005-6642-x","volume":"63","author":"Z Tu","year":"2005","unstructured":"Tu, Z., Chen, X., Yuille, A. L., & Zhu, S. C. (2005). Image parsing: Unifying segmentation, detection, and recognition. International Journal of Computer Vision, 63, 113.","journal-title":"International Journal of Computer Vision"},{"key":"795_CR41","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511721724","volume-title":"Energy landscapes: Applications to clusters, biomolecules and glasses","author":"D Wales","year":"2004","unstructured":"Wales, D. (2004). Energy landscapes: Applications to clusters, biomolecules and glasses. Cambridge: Cambridge Molecular Science, Cambridge University Press."},{"key":"795_CR42","doi-asserted-by":"crossref","unstructured":"Wu, C., Lenz, I., & Saxena, A. (2014). Hierarchical semantic labeling for task-relevant rgb-d perception. In Robotics: Science and systems (RSS).","DOI":"10.15607\/RSS.2014.X.006"},{"key":"795_CR43","unstructured":"Zhao, Y., & Zhu, S. C. (2011). Image parsing via stochastic scene grammar. In NIPS."},{"issue":"3","key":"795_CR44","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1109\/TPAMI.2009.189","volume":"32","author":"B Zheng","year":"2010","unstructured":"Zheng, B., Takamatsu, J., & Ikeuchi, K. (2010). An adaptive and stable method for fitting implicit polynomial curves and surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(3), 561\u2013568.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"795_CR45","doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhao, Y., Yu, J. C., Ikeuchi, K., & Zhu, S. C. (2013). Beyond point cloud: Scene understanding by reasoning geometry and physics. In CVPR.","DOI":"10.1109\/CVPR.2013.402"},{"key":"795_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, B., Zhao, Y., Yu, J. C., Ikeuchi, K., & Zhu, S. C. (2014). Detecting potential falling objects by inferring human action and natural disturbance. In IEEE international conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA.2014.6907351"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0795-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-014-0795-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0795-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T09:18:17Z","timestamp":1566292697000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-014-0795-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,28]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,4]]}},"alternative-id":["795"],"URL":"https:\/\/doi.org\/10.1007\/s11263-014-0795-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,28]]}}}