{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:56:07Z","timestamp":1777568167756,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":40,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642337147","type":"print"},{"value":"9783642337154","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33715-4_53","type":"book-chapter","created":{"date-parts":[[2012,9,26]],"date-time":"2012-09-26T08:06:38Z","timestamp":1348646798000},"page":"732-745","source":"Crossref","is-referenced-by-count":39,"title":["People Watching: Human Actions as a Cue for Single View Geometry"],"prefix":"10.1007","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","reference":[{"key":"53_CR1","volume-title":"The ecological approach to visual perception","author":"J. Gibson","year":"1979","unstructured":"Gibson, J.: The ecological approach to visual perception. Houghton Mifflin, Boston (1979)"},{"key":"53_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: People detection and articulated pose estimation. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"53_CR3","doi-asserted-by":"crossref","unstructured":"Yang, Y., Ramanan, D.: Articulated pose estimation using flexible mixtures of parts. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"53_CR4","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"53_CR5","doi-asserted-by":"crossref","unstructured":"Taylor, C.J.: Reconstruction of articulated objects from point correspondences in a single image. In: CVPR (2000)","DOI":"10.1006\/cviu.2000.0878"},{"key":"53_CR6","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459411"},{"key":"53_CR7","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A., Hebert, M.: Putting objects in perspective. In: IJCV (2008)","DOI":"10.1007\/s11263-008-0137-5"},{"key":"53_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/978-3-642-15567-3_17","volume-title":"Computer Vision \u2013 ECCV 2010","author":"V. Hedau","year":"2010","unstructured":"Hedau, V., Hoiem, D., Forsyth, D.: Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol.\u00a06316, pp. 224\u2013237. Springer, Heidelberg (2010)"},{"key":"53_CR9","doi-asserted-by":"crossref","unstructured":"Yu, S.X., Zhang, H., Malik, J.: Inferring spatial layout from a single image via depth-ordered grouping. In: The 6th IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (2008)","DOI":"10.1109\/CVPRW.2008.4562977"},{"key":"53_CR10","unstructured":"Lee, D., Gupta, A., Hebert, M., Kanade, T.: Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In: NIPS (2010)"},{"key":"53_CR11","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A., Hebert, M.: Geometric context from a single image. In: ICCV (2005)","DOI":"10.1109\/ICCV.2005.107"},{"key":"53_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-3-642-15552-9_32","volume-title":"Computer Vision \u2013 ECCV 2010","author":"H. Wang","year":"2010","unstructured":"Wang, H., Gould, S., Koller, D.: Discriminative Learning with Latent Variables for Cluttered Indoor Scene Understanding. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 435\u2013449. Springer, Heidelberg (2010)"},{"key":"53_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/978-3-642-15561-1_35","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A. Gupta","year":"2010","unstructured":"Gupta, A., Efros, A., Hebert, M.: Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol.\u00a06314, pp. 482\u2013496. Springer, Heidelberg (2010)"},{"key":"53_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-642-15552-9_5","volume-title":"Computer Vision \u2013 ECCV 2010","author":"O. Barinova","year":"2010","unstructured":"Barinova, O., Lempitsky, V., Tretyak, E., Kohli, P.: Geometric Image Parsing in Man-Made Environments. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 57\u201370. Springer, Heidelberg (2010)"},{"key":"53_CR15","doi-asserted-by":"crossref","unstructured":"Del Pero, L., Guan, J., Brau, E., Schlecht, J., Barnard, K.: Sampling bedrooms. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995737"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Payet, N., Todorovic, S.: Scene shape from texture of objects. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995326"},{"key":"53_CR17","doi-asserted-by":"crossref","unstructured":"Schwing, A., Hazan, T., Pollefeys, M., Urtasun, R.: Efficient structured prediction for 3D indoor scene understanding. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248006"},{"key":"53_CR18","doi-asserted-by":"crossref","unstructured":"Del Pero, L., Bowdish, J., Fried, D., Kermgard, B., Hartley, E.L., Barnard, K.: Bayesian geometric modeling of indoor scenes. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247994"},{"key":"53_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, A., Davis, L.S.: Objects in action: An approach for combining action understanding and object perception. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383331"},{"key":"53_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-642-15552-9_48","volume-title":"Computer Vision \u2013 ECCV 2010","author":"M. Turek","year":"2010","unstructured":"Turek, M., Hoogs, A., Collins, R.: Unsupervised Learning of Functional Categories in Video Scenes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol.\u00a06312, pp. 664\u2013677. Springer, Heidelberg (2010)"},{"key":"53_CR21","unstructured":"Delaitre, V., Sivic, J., Laptev, I.: Learning person-object interactions for action recognition in still images. In: NIPS (2011)"},{"key":"53_CR22","doi-asserted-by":"crossref","unstructured":"Prest, A., Schmid, C., Ferrari, V.: Weakly supervised learning of interactions between humans and objects. PAMI (2011)","DOI":"10.1109\/TPAMI.2011.158"},{"key":"53_CR23","doi-asserted-by":"crossref","unstructured":"Gall, J., Fossati, A., van Gool, L.: Functional categorization of objects using real-time markerless motion capture. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995582"},{"key":"53_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/978-3-540-88688-4_25","volume-title":"Computer Vision \u2013 ECCV 2008","author":"H. Kjellstrom","year":"2008","unstructured":"Kjellstrom, H., Romero, J., Martinez, D., Kragic, D.: Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol.\u00a05303, pp. 336\u2013349. Springer, Heidelberg (2008)"},{"key":"53_CR25","doi-asserted-by":"crossref","unstructured":"Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for static human-object interactions. In: SMiCV, CVPR (2010)","DOI":"10.1109\/CVPRW.2010.5543176"},{"key":"53_CR26","unstructured":"Yao, B., Khosla, A., Fei-Fei, L.: Classifying actions and measuring action similarity by modeling the mutual context of objects and human poses. In: Proc. ICML (2011)"},{"key":"53_CR27","doi-asserted-by":"crossref","unstructured":"Gupta, A., Chen, T., Chen, F., Kimber, D., Davis, L.: Context and observation driven latent variable model for human pose estimation. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587511"},{"key":"53_CR28","doi-asserted-by":"crossref","unstructured":"Grabner, H., Gall, J., van Gool, L.: What makes a chair a chair? In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995327"},{"key":"53_CR29","doi-asserted-by":"crossref","unstructured":"Gupta, A., Satkin, S., Efros, A., Hebert, M.: From 3d scene geometry to human workspace. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"53_CR30","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3D human pose annotations. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"53_CR31","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"53_CR32","unstructured":"Guan, L., Franco, J.S., Pollefeys, M.: 3d occlusion inference from silhouette cues. In: CVPR (2007)"},{"key":"53_CR33","doi-asserted-by":"crossref","unstructured":"Krahnstoever, N., Mendonca, P.R.S.: Bayesian autocalibration for surveillance. In: CVPR (2005)","DOI":"10.1109\/ICCV.2005.44"},{"key":"53_CR34","doi-asserted-by":"crossref","unstructured":"Rother, D., Patwardhan, K., Sapiro, G.: What can casual walkers tell us about the 3D scene. In: CVPR (2007)","DOI":"10.21236\/ADA478460"},{"key":"53_CR35","unstructured":"Schodl, A., Essa, I.: Depth layers from occlusions. In: CVPR (2001)"},{"key":"53_CR36","unstructured":"Coughlan, J., Yuille, A.: The Manhattan world assumption: Regularities in scene statistics which enable bayesian inference. In: NIPS (2000)"},{"key":"53_CR37","doi-asserted-by":"crossref","unstructured":"Lee, D., Hebert, M., Kanade, T.: Geometric reasoning for single image structure recovery. In: ICCV (2009)","DOI":"10.1109\/CVPR.2009.5206872"},{"key":"53_CR38","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)"},{"key":"53_CR39","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., Forsyth, D.: Recovering free space of indoor scenes from a single image. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248005"},{"key":"53_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1007\/978-3-642-33783-3_21","volume-title":"ECCV 2012","author":"V. Delaitre","year":"2012","unstructured":"Delaitre, V., Fouhey, D.F., Laptev, I., Sivic, J., Gupta, A., Efros, A.A.: Scene Semantics from Long-Term Observation of People. In: Fitzgibbon, A., Lazebnik, S., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol.\u00a07577, pp. 284\u2013298. Springer, Heidelberg (2012)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2012"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33715-4_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T16:27:49Z","timestamp":1643473669000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33715-4_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642337147","9783642337154"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33715-4_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}