{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:09:19Z","timestamp":1758272959774,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,7,3]],"date-time":"2015-07-03T00:00:00Z","timestamp":1435881600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,7,3]],"date-time":"2015-07-03T00:00:00Z","timestamp":1435881600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP110102166"],"award-info":[{"award-number":["DP110102166"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP150104251"],"award-info":[{"award-number":["DP150104251"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE120102960"],"award-info":[{"award-number":["DE120102960"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s11263-015-0843-8","type":"journal-article","created":{"date-parts":[[2015,7,2]],"date-time":"2015-07-02T07:40:11Z","timestamp":1435822811000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Integrating Geometrical Context for Semantic Labeling of Indoor Scenes using RGBD Images"],"prefix":"10.1007","volume":"117","author":[{"given":"Salman H.","family":"Khan","sequence":"first","affiliation":[]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]},{"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[]},{"given":"Roberto","family":"Togneri","sequence":"additional","affiliation":[]},{"given":"Imran","family":"Naseem","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,7,3]]},"reference":[{"issue":"5","key":"843_CR1","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","volume":"33","author":"P Arbelaez","year":"2011","unstructured":"Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour detection and hierarchical image segmentation. TPAMI, 33(5), 898\u2013916.","journal-title":"TPAMI"},{"key":"843_CR2","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/8579.001.0001","volume-title":"Markov random fields for vision and image processing","author":"A Blake","year":"2011","unstructured":"Blake, A., Kohli, P., & Rother, C. (2011). Markov random fields for vision and image processing. Cambridge: The MIT Press."},{"issue":"2","key":"843_CR3","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11263-006-7934-5","volume":"70","author":"Y Boykov","year":"2006","unstructured":"Boykov, Y., & Funka-Lea, G. (2006). Graph cuts and efficient nd image segmentation. IJCV, 70(2), 109\u2013131.","journal-title":"IJCV"},{"issue":"11","key":"843_CR4","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1109\/34.969114","volume":"23","author":"Y Boykov","year":"2001","unstructured":"Boykov, Y., Veksler, O., & Zabih, R. (2001). Fast approximate energy minimization via graph cuts. TPAMI, 23(11), 1222\u20131239.","journal-title":"TPAMI"},{"issue":"0885\u20136125","key":"843_CR5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45(0885\u20136125), 5\u201332.","journal-title":"Machine Learning"},{"key":"843_CR6","doi-asserted-by":"crossref","unstructured":"Cadena, C., & Ko\u0161eck\u00e1, J. (2014). Semantic segmentation with heterogeneous sensor coverages.","DOI":"10.1109\/ICRA.2014.6907237"},{"issue":"7","key":"843_CR7","doi-asserted-by":"publisher","first-page":"1312","DOI":"10.1109\/TPAMI.2011.231","volume":"34","author":"J Carreira","year":"2012","unstructured":"Carreira, J., & Sminchisescu, C. (2012). Cpmc: Automatic object segmentation using constrained parametric min-cuts. TPAMI, 34(7), 1312\u20131328.","journal-title":"TPAMI"},{"key":"843_CR8","unstructured":"Couprie, C., Farabet, C., Najman, L., & LeCun, Y.(2013). Indoor semantic segmentation using depth information. ICLR."},{"key":"843_CR9","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, vol\u00a01 (pp 886\u2013893).","DOI":"10.1109\/CVPR.2005.177"},{"key":"843_CR10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511611308","volume-title":"Advances in decision analysis: from foundations to applications","author":"W Edwards","year":"2007","unstructured":"Edwards, W., Miles, R. F, Jr, & Von Winterfeldt, D. (2007). Advances in decision analysis: from foundations to applications. Cambridge: Cambridge University Press."},{"issue":"8","key":"843_CR11","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013). Learning hierarchical features for scene labeling. TPAMI, 35(8), 1915\u20131929. doi:\n                    10.1109\/TPAMI.2012.231\n                    \n                  .","journal-title":"TPAMI"},{"issue":"2","key":"843_CR12","doi-asserted-by":"publisher","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. IJCV, 59(2), 167\u2013181.","journal-title":"IJCV"},{"issue":"1","key":"843_CR13","first-page":"32","volume":"21","author":"K Fukunaga","year":"1975","unstructured":"Fukunaga, K., & Hostetler, L. (1975). The estimation of the gradient of a density function, with applications in pattern recognition. TIT, 21(1), 32\u201340.","journal-title":"TIT"},{"key":"843_CR14","doi-asserted-by":"crossref","unstructured":"Gould, S., Fulton, R., & Koller, D. (2009). Decomposing a scene into geometric and semantically consistent regions. In IEEE ICCV (pp 1\u20138).","DOI":"10.1109\/ICCV.2009.5459211"},{"key":"843_CR15","doi-asserted-by":"crossref","unstructured":"Gulshan, V., Rother, C., Criminisi, A., Blake, A., & Zisserman, A. (2010). Geodesic star convexity for interactive image segmentation. In IEEE CVPR (pp 3129\u20133136).","DOI":"10.1109\/CVPR.2010.5540073"},{"key":"843_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, S., Arbelaez, P., & Malik, J. (2013), Perceptual organization and recognition of indoor scenes from rgb-d images. In IEEE CVPR (pp. 564\u2013571).","DOI":"10.1109\/CVPR.2013.79"},{"key":"843_CR17","doi-asserted-by":"crossref","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez. P., & Malik, J. (2014). Learning rich features from rgb-d images for object detection and segmentation. In Computer Vision\u2013ECCV 2014 (pp. 345\u2013360). Springer.","DOI":"10.1007\/978-3-319-10584-0_23"},{"issue":"1","key":"843_CR18","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009). The weka data mining software: An update. ACM SIGKDD, 11(1), 10\u201318.","journal-title":"ACM SIGKDD"},{"issue":"4","key":"843_CR19","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1109\/TPAMI.2014.2353635","volume":"37","author":"M Hayat","year":"2015","unstructured":"Hayat, M., Bennamoun, M., & An, S. (2015). Deep reconstruction models for image set classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(4), 713\u2013727. doi:\n                    10.1109\/TPAMI.2014.2353635\n                    \n                  .","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"843_CR20","unstructured":"He, X., Zemel, R. S., & Carreira-Perpin\u00e1n, M. A. (2004). Multiscale conditional random fields for image labeling. In IEEE CVPR, vol\u00a02 (pp II\u2013695)."},{"key":"843_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Q., Han, M., Wu, B., & Ioffe, S. (2011). A hierarchical conditional random field model for labeling and segmenting images of street scenes. In IEEE CVPR (pp. 1953\u20131960).","DOI":"10.1109\/CVPR.2011.5995571"},{"key":"843_CR22","doi-asserted-by":"crossref","unstructured":"Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A., et\u00a0al (2011). Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera. In ACM Proceedings of the 24th annual ACM symposium on User interface software and technology (pp. 559\u2013568).","DOI":"10.1145\/2047196.2047270"},{"issue":"9","key":"843_CR23","first-page":"1021","volume":"31","author":"Y Jiang","year":"2012","unstructured":"Jiang, Y., Lim, M., Zheng, C., & Saxena, A. (2012). Learning to place new objects in a scene. IJRR, 31(9), 1021\u20131043.","journal-title":"IJRR"},{"issue":"1","key":"843_CR24","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1258\/rsmmlj.77.1.27","volume":"77","author":"T Joachims","year":"2009","unstructured":"Joachims, T., Finley, T., & Yu, C. N. J. (2009). Cutting-plane training of structural svms. JML, 77(1), 27\u201359.","journal-title":"JML"},{"issue":"5","key":"843_CR25","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/34.765655","volume":"21","author":"AE Johnson","year":"1999","unstructured":"Johnson, A. E., & Hebert, M. (1999). Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(5), 433\u2013449.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"843_CR26","doi-asserted-by":"crossref","unstructured":"Khan, S., Bennamoun, M., Sohel, F., & Togneri, R. (2014a). Automatic feature learning for robust shadow detection. In IEEE CVPR.","DOI":"10.1109\/CVPR.2014.249"},{"key":"843_CR27","doi-asserted-by":"crossref","unstructured":"Khan, S., He, X., Bennamoun, M., Sohel, F., & Togneri, R. (2015). Separating objects and clutter in indoor scenes. In IEEE CVPR.","DOI":"10.1109\/CVPR.2015.7299091"},{"key":"843_CR28","doi-asserted-by":"crossref","unstructured":"Khan, S. H., Bennamoun, M., Sohel, F., & Togneri, R. (2014b). Geometry driven semantic labeling of indoor scenes. In Computer Vision\u2013ECCV 2014 (pp. 679\u2013694). Springer.","DOI":"10.1007\/978-3-319-10590-1_44"},{"key":"843_CR29","doi-asserted-by":"crossref","unstructured":"Kohli, P., Kumar, M. P., & Torr, P. H. (2007). P3 & beyond: Solving energies with higher order cliques. In IEEE CVPR (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383204"},{"issue":"3","key":"843_CR30","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-008-0202-0","volume":"82","author":"P Kohli","year":"2009","unstructured":"Kohli, P., Torr, P. H., et al. (2009). Robust higher order potentials for enforcing label consistency. IJCV, 82(3), 302\u2013324.","journal-title":"IJCV"},{"key":"843_CR31","unstructured":"Koppula, H. S., Anand, A., Joachims, T., & Saxena ,A. (2011). Semantic labeling of 3d point clouds for indoor scenes. In NIPS (pp. 244\u2013252)."},{"key":"843_CR32","unstructured":"Kr\u00e4henb\u00fchl, P., & Koltun, V. (2011). Efficient inference in fully connected crfs with gaussian edge potentials. In NIPS (pp. 109\u2013117)."},{"key":"843_CR33","doi-asserted-by":"crossref","unstructured":"Ladicky, L., Russell, C., Kohli, P., & Torr, P. H. (2009). Associative hierarchical crfs for object class image segmentation. In IEEE ICCV (pp. 739\u2013746).","DOI":"10.1109\/ICCV.2009.5459248"},{"key":"843_CR34","doi-asserted-by":"crossref","unstructured":"Ladick\u1ef3, L., Russell, C., Kohli, P., & Torr, P. H. (2013). Inference methods for crfs with co-occurrence statistics. In IJCV (pp. 1\u201313).","DOI":"10.1007\/s11263-012-0583-y"},{"key":"843_CR35","doi-asserted-by":"crossref","unstructured":"Lai, K., Bo, L., Ren, X., & Fox, D. (2011). A large-scale hierarchical multi-view rgb-d object dataset. In IEEE ICRA (pp. 1817\u20131824).","DOI":"10.1109\/ICRA.2011.5980382"},{"key":"843_CR36","unstructured":"Lempitsky, V., Vedaldi, A., & Zisserman, A. (2011). Pylon model for semantic segmentation. In NIPS (pp. 1485\u20131493)."},{"key":"843_CR37","doi-asserted-by":"crossref","unstructured":"Li, Y., Tarlow, D., & Zemel, R. (2013). Exploring compositional high order pattern potentials for structured output learning. In IEEE CVPR (pp. 49\u201356).","DOI":"10.1109\/CVPR.2013.14"},{"issue":"2","key":"843_CR38","doi-asserted-by":"publisher","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. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"issue":"7","key":"843_CR39","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala, T., Pietikainen, M., & Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971\u2013987.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"843_CR40","doi-asserted-by":"publisher","unstructured":"Quattoni, A., & Torralba, A. (2009). Recognizing indoor scenes. In CVPR (pp. 413\u2013420). doi:\n                    10.1109\/CVPR.2009.5206537\n                    \n                  .","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"843_CR41","doi-asserted-by":"crossref","unstructured":"Quigley, M., Batra, S., Gould, S., Klingbeil, E., Le, Q., Wellman, A., & Ng, A. Y. (2009). High-accuracy 3d sensing for mobile manipulation: Improving object detection and door opening. In IEEE ICRA (pp. 2816\u20132822).","DOI":"10.1109\/ROBOT.2009.5152750"},{"issue":"5","key":"843_CR42","first-page":"248","volume":"36","author":"T Rabbani","year":"2006","unstructured":"Rabbani, T., van Den Heuvel, F., & Vosselmann, G. (2006). Segmentation of point clouds using smoothness constraint. IAPR SSIS, 36(5), 248\u2013253.","journal-title":"IAPR SSIS"},{"key":"843_CR43","doi-asserted-by":"crossref","unstructured":"Rao, D., Le, Q. V., Phoka, T., Quigley, M., Sudsang, A., & Ng, A. Y. (2010). Grasping novel objects with depth segmentation. In IEEE IROS (pp. 2578\u20132585).","DOI":"10.1109\/IROS.2010.5650493"},{"key":"843_CR44","unstructured":"Ren, X., Bo, L., & Fox, D. (2012). Rgb-(d) scene labeling: Features and algorithms. In IEEE CVPR (pp. 2759\u20132766)."},{"key":"843_CR45","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V., & Blake, A. (2004). Grabcut: Interactive foreground extraction using iterated graph cuts. TOG, ACM, 23, 309\u2013314.","journal-title":"TOG, ACM"},{"issue":"1","key":"843_CR46","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s11263-007-0109-1","volume":"81","author":"J Shotton","year":"2009","unstructured":"Shotton, J., Winn, J., Rother, C., & Criminisi, A. (2009). Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV, 81(1), 2\u201323.","journal-title":"IJCV"},{"key":"843_CR47","doi-asserted-by":"crossref","unstructured":"Silberman, N., & Fergus, R. (2011). Indoor scene segmentation using a structured light sensor. In IEEE ICCV Workshops (pp. 601\u2013608).","DOI":"10.1109\/ICCVW.2011.6130298"},{"key":"843_CR48","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from rgbd images. In ECCV (pp. 746\u2013760). Springer.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"843_CR49","doi-asserted-by":"crossref","unstructured":"Szummer, M., Kohli, P., & Hoiem, D. (2008). Learning crfs using graph cuts. In ECCV (pp 582\u2013595). Springer.","DOI":"10.1007\/978-3-540-88688-4_43"},{"key":"843_CR50","doi-asserted-by":"crossref","unstructured":"Tsochantaridis, I., Hofmann, T., Joachims, T., & Altun, Y. (2004). Support vector machine learning for interdependent and structured output spaces. In ACM ICML (p 104).","DOI":"10.1145\/1015330.1015341"},{"key":"843_CR51","unstructured":"Van De\u00a0Weijer, J., & Schmid, C. (2006). Coloring local feature extraction. In ECCV (pp 334\u2013348). Springer"},{"issue":"4","key":"843_CR52","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1109\/TPAMI.2008.300","volume":"32","author":"RG Von Gioi","year":"2010","unstructured":"Von Gioi, R. G., Jakubowicz, J., Morel, J. M., & Randall, G. (2010). Lsd: A fast line segment detector with a false detection control. TPAMI, 32(4), 722\u2013732.","journal-title":"TPAMI"},{"key":"843_CR53","doi-asserted-by":"crossref","unstructured":"Woodford, O. J., Rother, C., & Kolmogorov, V. (2009). A global perspective on map inference for low-level vision. In IEEE ICCV (pp. 2319\u20132326).","DOI":"10.1109\/ICCV.2009.5459434"},{"key":"843_CR54","doi-asserted-by":"crossref","unstructured":"Xiao, J., Owens, A., & Torralba, A. (2013). Sun3d: A database of big spaces reconstructed using sfm and object labels. In IEEE ICCV","DOI":"10.1109\/ICCV.2013.458"},{"key":"843_CR55","doi-asserted-by":"crossref","unstructured":"Xiong, X., & Huber, D. (2010). Using context to create semantic 3d models of indoor environments. In BMVC (pp. 45\u20131).","DOI":"10.5244\/C.24.45"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-015-0843-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-015-0843-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-015-0843-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-015-0843-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T07:13:57Z","timestamp":1589699637000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-015-0843-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,3]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["843"],"URL":"https:\/\/doi.org\/10.1007\/s11263-015-0843-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2015,7,3]]},"assertion":[{"value":"23 November 2014","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2015","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}