{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:06:22Z","timestamp":1760346382213},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2014,3,22]],"date-time":"2014-03-22T00:00:00Z","timestamp":1395446400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1007\/s11263-014-0710-z","type":"journal-article","created":{"date-parts":[[2014,3,21]],"date-time":"2014-03-21T16:45:26Z","timestamp":1395420326000},"page":"259-274","source":"Crossref","is-referenced-by-count":43,"title":["People Watching: Human Actions as a Cue for Single View Geometry"],"prefix":"10.1007","volume":"110","author":[{"given":"David F.","family":"Fouhey","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Delaitre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexei A.","family":"Efros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,3,22]]},"reference":[{"key":"710_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., & Schiele, B. (2009). Pictorial structures revisited: People detection and articulated pose estimation. In CVPR.","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"710_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., & Schiele, B. (2010). Monocular 3D pose estimation and tracking by detection. In CVPR.","DOI":"10.1109\/CVPR.2010.5540156"},{"key":"710_CR3","doi-asserted-by":"crossref","unstructured":"Barinova, O., Lempitsky, V., Tretyak, E., & Kohli, P. (2010). Geometric image parsing in man-made environments. In ECCV.","DOI":"10.1007\/978-3-642-15552-9_5"},{"key":"710_CR4","doi-asserted-by":"crossref","unstructured":"Bourdev, L., & Malik, J. (2009). Poselets: Body part detectors trained using 3D human pose annotations. In ICCV.","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"710_CR5","doi-asserted-by":"crossref","unstructured":"Choi, W., Chao, Y.W., Pantofaru, C., & Savarese, S. (2013). Understanding indoor scenes using 3D geometric phrases. In CVPR.","DOI":"10.1109\/CVPR.2013.12"},{"key":"710_CR6","unstructured":"Coughlan, J., & Yuille, A. (2000). The Manhattan world assumption: Regularities in scene statistics which enable bayesian inference. In NIPS."},{"key":"710_CR7","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":"710_CR8","unstructured":"Del Pero, L., Bowdish, J., Fried, D., Kermgard, B., Hartley, E. L., & Barnard, K. (2012). Bayesian geometric modeling of indoor scenes. In CVPR."},{"key":"710_CR9","unstructured":"Del Pero, L., Guan, J., Brau, E., Schlecht, J., & Barnard, K. (2011). Sampling bedrooms. In CVPR."},{"key":"710_CR10","doi-asserted-by":"crossref","unstructured":"Delaitre, V., Fouhey, D., Laptev, I., Sivic, J., Efros, A., & Gupta, A. (2012). Scene semantics from long-term observation of people. In ECCV.","DOI":"10.1007\/978-3-642-33783-3_21"},{"key":"710_CR11","unstructured":"Delaitre, V., Sivic, J., & Laptev, I. (2011). Learning person\u2013object interactions for action recognition in still images. In NIPS."},{"key":"710_CR12","doi-asserted-by":"crossref","unstructured":"Desai, C., Ramanan, D., & Fowlkes, C. (2010). Discriminative models for static human\u2013object interactions. In SMiCV, CVPR.","DOI":"10.1109\/CVPRW.2010.5543176"},{"issue":"397","key":"710_CR13","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1080\/01621459.1987.10478410","volume":"82","author":"B Efron","year":"1987","unstructured":"Efron, B. (1987). Better bootstrap confidence intervals. Journal of the American Statistical Association, 82(397), 171\u2013185.","journal-title":"Journal of the American Statistical Association"},{"key":"710_CR14","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., & Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In CVPR.","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"710_CR15","doi-asserted-by":"crossref","unstructured":"Flint, A., Murray, D., & Reid, I. (2011). Manhattan scene understanding using monocular, stereo, and 3D features. In ICCV.","DOI":"10.1109\/ICCV.2011.6126501"},{"key":"710_CR16","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":"710_CR17","doi-asserted-by":"crossref","unstructured":"Fouhey, D.F., Gupta, A., & Hebert, M. (2013). Data-driven 3D primitives for single image understanding. In ICCV.","DOI":"10.1109\/ICCV.2013.421"},{"key":"710_CR18","doi-asserted-by":"crossref","unstructured":"Gall, J., Fossati, A., & van Gool, L. (2011). Functional categorization of objects using real-time markerless motion capture. In CVPR.","DOI":"10.1109\/CVPR.2011.5995582"},{"key":"710_CR19","volume-title":"The ecological approach to visual perception","author":"J Gibson","year":"1979","unstructured":"Gibson, J. (1979). The ecological approach to visual perception. Boston: Houghton Mifflin."},{"key":"710_CR20","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., & van Gool, L. (2011). What makes a chair a chair? In CVPR.","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"710_CR21","unstructured":"Guan, L., Franco, J.S., & Pollefeys, M. (2007). 3D occlusion inference from silhouette cues. In CVPR."},{"key":"710_CR22","doi-asserted-by":"crossref","unstructured":"Gupta, A., & Davis, L. S. (2007). Objects in action: An approach for combining action understanding and object perception. In CVPR.","DOI":"10.1109\/CVPR.2007.383331"},{"key":"710_CR23","doi-asserted-by":"crossref","unstructured":"Gupta, A., Chen, T., Chen, F., Kimber, D., & Davis, L. (2008). Context and observation driven latent variable model for human pose estimation. In CVPR.","DOI":"10.1109\/CVPR.2008.4587511"},{"key":"710_CR24","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":"710_CR25","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":"710_CR26","doi-asserted-by":"crossref","unstructured":"Hartley, R. I., & Zisserman, A. (2004). Multiple view geometry in computer vision (2nd ed.). Cambridge University Press, Cambridge, ISBN: 0521540518.","DOI":"10.1017\/CBO9780511811685"},{"key":"710_CR27","unstructured":"Hedau, V., Hoiem, D., & Forsyth, D. (2009). Recovering the spatial layout of cluttered rooms. In: ICCV."},{"key":"710_CR28","unstructured":"Hedau, V., Hoiem, D., & Forsyth, D. (2010). Thinking inside the box: Using appearance models and context based on room geometry. In: ECCV."},{"key":"710_CR29","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A., & Hebert, M. (2005). Geometric context from a single image. In ICCV.","DOI":"10.1109\/ICCV.2005.107"},{"key":"710_CR30","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A., & Hebert, M. (2008). Putting objects in perspective. In IJCV.","DOI":"10.1007\/s11263-008-0137-5"},{"key":"710_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, Y., & Saxena, A. (2013). Hallucinated humans as the hidden context for labeling 3D scenes. In CVPR.","DOI":"10.1109\/CVPR.2013.385"},{"key":"710_CR32","unstructured":"Johnson, S., & Everingham, M. (2011). Learning effective human pose estimation from inaccurate annotation. In: CVPR."},{"issue":"1","key":"710_CR33","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/0004-3702(81)90031-X","volume":"17","author":"T Kanade","year":"1981","unstructured":"Kanade, T. (1981). Recovery of the three-dimensional shape of an object from a single view. Artificial Intelligence, 17(1), 409\u2013460.","journal-title":"Artificial Intelligence"},{"key":"710_CR34","doi-asserted-by":"crossref","unstructured":"Karsch, K., Liu, C., & Kang, S.B. (2012). Depth extraction from video using non-parametric sampling. In ECCV.","DOI":"10.1007\/978-3-642-33715-4_56"},{"key":"710_CR35","doi-asserted-by":"crossref","unstructured":"Kjellstrom, H., Romero, J., Martinez, D., & Kragic, D. (2008). Simultaneous visual recognition of manipulation actions and manipulated objects. In ECCV.","DOI":"10.1007\/978-3-540-88688-4_25"},{"key":"710_CR36","doi-asserted-by":"crossref","unstructured":"Krahnstoever, N., & Mendonca, P. R. S. (2005). Bayesian autocalibration for surveillance. In CVPR.","DOI":"10.1109\/ICCV.2005.44"},{"key":"710_CR37","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":"710_CR38","doi-asserted-by":"crossref","unstructured":"Lee, D., Hebert, M., & Kanade, T. (2009). Geometric reasoning for single image structure recovery. In ICCV.","DOI":"10.1109\/CVPR.2009.5206872"},{"key":"710_CR39","doi-asserted-by":"crossref","unstructured":"Park, D., & Ramanan, D. (2011). N-best maximal decoders for part models. In ICCV.","DOI":"10.1109\/ICCV.2011.6126552"},{"key":"710_CR40","doi-asserted-by":"crossref","unstructured":"Payet, N., & Todorovic, S. (2011). Scene shape from texture of objects. In CVPR.","DOI":"10.1109\/CVPR.2011.5995326"},{"key":"710_CR41","unstructured":"Prest, A., Schmid, C., & Ferrari, V. (2011). Weakly supervised learning of interactions between humans and objects. In PAMI."},{"key":"710_CR42","doi-asserted-by":"crossref","unstructured":"Ramakrishna, V., Kanade, T., & Sheikh, Y. (2013). Tracking human pose by tracking symmetric parts. In CVPR.","DOI":"10.1109\/CVPR.2013.478"},{"key":"710_CR43","doi-asserted-by":"crossref","unstructured":"Rother, C. (2002). A new approach to vanishing point detection in architectural environments. In IVC 20.","DOI":"10.1016\/S0262-8856(02)00054-9"},{"key":"710_CR44","doi-asserted-by":"crossref","unstructured":"Rother, D., Patwardhan, K., & Sapiro, G. (2007). What can casual walkers tell us about the 3D scene. In CVPR.","DOI":"10.21236\/ADA478460"},{"key":"710_CR45","unstructured":"Saxena, A., Sun, M., & Ng, A. Y. (2008). Make3D: Learning 3D scene structure from a single still image. In TPAMI."},{"key":"710_CR46","doi-asserted-by":"crossref","unstructured":"Schodl, A., & Essa, I. (2001). Depth layers from occlusions. In CVPR.","DOI":"10.1109\/CVPR.2001.990534"},{"key":"710_CR47","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":"710_CR48","doi-asserted-by":"crossref","unstructured":"Schwing, A.G., Fidler, S., Pollefeys, M., & Urtasun, R. (2013). Box in the box: Joint 3D layout and object reasoning from single images. In ICCV.","DOI":"10.1109\/ICCV.2013.51"},{"key":"710_CR49","unstructured":"Taylor, C. J. (2000). Reconstruction of articulated objects from point correspondences in a single image. In: CVPR."},{"key":"710_CR50","doi-asserted-by":"crossref","unstructured":"Turek, M., Hoogs, A., & Collins, R. (2010). Unsupervised learning of functional categories in video scenes. In ECCV.","DOI":"10.1007\/978-3-642-15552-9_48"},{"key":"710_CR51","unstructured":"Wang, H., Gould, S., & Koller, D. (2010). Discriminative learning with latent variables for cluttered indoor scene understanding. In ECCV."},{"key":"710_CR52","unstructured":"Xiao, J., Russell, B., & Torralba, A. (2012). Localizing 3D cuboids in single-view images. In NIPS."},{"key":"710_CR53","unstructured":"Yang, Y., & Ramanan, D. (2011). Articulated pose estimation using flexible mixtures of parts. In: CVPR."},{"key":"710_CR54","unstructured":"Yao, B., Khosla, A., & Fei-Fei, L. (2011). Classifying actions and measuring action similarity by modeling the mutual context of objects and human poses. In Proceedings of the ICML."},{"key":"710_CR55","doi-asserted-by":"crossref","unstructured":"Yu, S. X., Zhang, H., & Malik, J. (2008). Inferring spatial layout from a single image via depth-ordered grouping. In 6th Workshop on Perceptual Organization in Computer Vision.","DOI":"10.1109\/CVPRW.2008.4562977"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0710-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-014-0710-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0710-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T15:52:26Z","timestamp":1565279546000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-014-0710-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3,22]]},"references-count":55,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["710"],"URL":"https:\/\/doi.org\/10.1007\/s11263-014-0710-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3,22]]}}}