{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:44:56Z","timestamp":1777995896031,"version":"3.51.4"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,11,12]],"date-time":"2014-11-12T00:00:00Z","timestamp":1415750400000},"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\/s11263-014-0779-4","type":"journal-article","created":{"date-parts":[[2014,11,14]],"date-time":"2014-11-14T18:58:43Z","timestamp":1415991523000},"page":"204-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Indoor Scene Understanding with Geometric and Semantic Contexts"],"prefix":"10.1007","volume":"112","author":[{"given":"Wongun","family":"Choi","sequence":"first","affiliation":[]},{"given":"Yu-Wei","family":"Chao","sequence":"additional","affiliation":[]},{"given":"Caroline","family":"Pantofaru","sequence":"additional","affiliation":[]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,11,12]]},"reference":[{"key":"779_CR1","doi-asserted-by":"crossref","unstructured":"Bao, S., Sun, M., & Savarese, S. (2010). Toward coherent object detection and scene layout understanding. In Proceedings of the conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2010.5540229"},{"key":"779_CR2","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C. C., & Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol., 2, 27:1\u201327:27.","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"779_CR3","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Choi, W., Pantofaru, C., & Savarese, S. (2013). Layout estimation of highly cluttered indoor scenes using geometric and semantic cues. In Proceedings of the International Conference on Image Analysis and Processing.","DOI":"10.1007\/978-3-642-41184-7_50"},{"key":"779_CR4","doi-asserted-by":"crossref","unstructured":"Choi, W., Chao, Y., Pantofaru, C., & Savarese, S. (2013) Understanding indoor scenes using 3D geometric phrases. In CVPR.","DOI":"10.1109\/CVPR.2013.12"},{"key":"779_CR5","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In CVPR.","DOI":"10.1109\/CVPR.2005.177"},{"key":"779_CR6","doi-asserted-by":"crossref","unstructured":"Desai, C., Ramanan, D., & Fowlkes, C. C. (2011). Discriminative models for multi-class object layout. IJCV.","DOI":"10.1007\/s11263-011-0439-x"},{"key":"779_CR7","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The Pascal Visual Object Classes (VOC) challenge. IJCV.","DOI":"10.1007\/s11263-009-0275-4"},{"key":"779_CR8","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., & Perona, P. (2005). A bayesian hierarchical model for learning natural scene categories. CVPR pp. 524\u2013531.","DOI":"10.1109\/CVPR.2005.16"},{"issue":"9","key":"779_CR9","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"P Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P., Girshick, R., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part based models. PAMI, 32(9), 1627\u20131645.","journal-title":"PAMI"},{"key":"779_CR10","doi-asserted-by":"crossref","unstructured":"Fouhey, D. F., Delaitre, V., Gupta, A., Efros, A. 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":"779_CR11","unstructured":"Geiger, A., Wojek, C., & Urtasun, R. (2011). Joint 3D estimation of objects and scene layout. In NIPS."},{"key":"779_CR12","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":"779_CR13","doi-asserted-by":"crossref","unstructured":"Hartley, R. I., & Zisserman, A. (2004). Multiple View Geometry in Computer Vision (2nd ed.). Cambridge: Cambridge University Press, ISBN: 0521540518.","DOI":"10.1017\/CBO9780511811685"},{"key":"779_CR14","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., & Forsyth, D. (2009). Recovering the spatial layout of cluttered room. In ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459411"},{"key":"779_CR15","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":"779_CR16","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., & Forsyth, D. (2012). Recovering free space of indoor scenes from a single image. In CVPR.","DOI":"10.1109\/CVPR.2012.6248005"},{"key":"779_CR17","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A. A., & Hebert, M. (2007). Recovering surface layout from an image. IJCV.","DOI":"10.1007\/s11263-006-0031-y"},{"key":"779_CR18","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A. A., & Hebert, M. (2008). Putting objects in perspective. IJCV.","DOI":"10.1007\/s11263-008-0137-5"},{"issue":"1","key":"779_CR19","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1137\/S1052623496303470","volume":"9","author":"JC Lagarias","year":"1998","unstructured":"Lagarias, J. C., Reeds, J. A., Wright, M. H., & Wright, P. E. (1998). Convergence properties of the nelder-mead simplex method in low dimensions. SIAM Journal on Optimization, 9(1), 148\u2013158.","journal-title":"SIAM Journal on Optimization"},{"key":"779_CR20","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR.","DOI":"10.1109\/CVPR.2006.68"},{"key":"779_CR21","unstructured":"Lee, D., Gupta, A., Hebert, M., & Kanade, T. (2010). Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In NIPS."},{"key":"779_CR22","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":"779_CR23","unstructured":"Leibe, B., Leonardis, A., & Schiele, B. (2004). Combined object categorization and segmentation with an implicit shape model. In Statistical Learning in Computer Vision, ECCV."},{"key":"779_CR24","unstructured":"Li, C., Parikh, D., & Chen, T. (2012). Automatic discovery of groups of objects for scene understanding. In CVPR."},{"key":"779_CR25","unstructured":"Li, L. J., Su, H., Xing, E. P., & Fei-Fei, L. (2010). Object bank: A high-level image representation for scene classification & semantic feature sparsification. In NIPS."},{"issue":"2","key":"779_CR26","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. IJCV, 60(2), 91\u2013110. doi: 10.1023\/B:VISI.0000029664.99615.94 .","journal-title":"IJCV"},{"key":"779_CR27","doi-asserted-by":"crossref","unstructured":"Pandey, M., & Lazebnik, S. (2011). Scene recognition and weakly supervised object localization with deformable part-based models. In ICCV.","DOI":"10.1109\/ICCV.2011.6126383"},{"key":"779_CR28","unstructured":"Pero, L. D., Bowdish, J., Fried, D., Kermgard, B., Hartley, E. L., & Barnard, K. (2012). Bayesian geometric modeling of indoor scenes. In CVPR."},{"key":"779_CR29","doi-asserted-by":"crossref","unstructured":"Quattoni, A., & Torralba, A. (2009). Recognizing indoor scenes. In CVPR.","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"779_CR30","doi-asserted-by":"crossref","unstructured":"Rother, C. (2002). A new approach for vanishing point detection in architectural environments. Journal Image and Vision Computing, 20, 647\u2013656.","DOI":"10.1016\/S0262-8856(02)00054-9"},{"key":"779_CR31","doi-asserted-by":"crossref","unstructured":"Sadeghi, A., & Farhadi, A. (2011). Recognition using visual phrases. In CVPR.","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"779_CR32","doi-asserted-by":"crossref","unstructured":"Satkin, S., Lin, J., & Hebert, M. (2012). Data-driven scene understanding from 3D models. In BMVC.","DOI":"10.5244\/C.26.128"},{"key":"779_CR33","doi-asserted-by":"crossref","unstructured":"Schwing, A. G., & Urtasun, R. (2012). Efficient exact inference for 3D indoor scene understanding. In ECCV.","DOI":"10.1007\/978-3-642-33783-3_22"},{"key":"779_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., Gould, S., & Koller, D. (2010). Discriminative learning with latent variables for cluttered indoor scene understanding. In ECCV.","DOI":"10.1007\/978-3-642-15552-9_32"},{"key":"779_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., & Mori, G. (2011). Hidden part models for human action recognition: Probabilistic versus max margin. In PAMI.","DOI":"10.1109\/TPAMI.2010.214"},{"key":"779_CR36","doi-asserted-by":"crossref","unstructured":"Xiang, Y., & Savarese, S. (2012). Estimating the aspect layout of object categories. In CVPR.","DOI":"10.1109\/CVPR.2012.6248081"},{"key":"779_CR37","unstructured":"Zhao, Y., & Zhu, S. C. (2011). Image parsing via stochastic scene grammar. In NIPS."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0779-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-014-0779-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0779-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,17]],"date-time":"2019-08-17T11:09:04Z","timestamp":1566040144000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-014-0779-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,11,12]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,4]]}},"alternative-id":["779"],"URL":"https:\/\/doi.org\/10.1007\/s11263-014-0779-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,11,12]]}}}