{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:14:56Z","timestamp":1763468096726,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":33,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642337826"},{"type":"electronic","value":"9783642337833"}],"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\/978-3-642-33783-3_21","type":"book-chapter","created":{"date-parts":[[2012,9,26]],"date-time":"2012-09-26T08:07:09Z","timestamp":1348646829000},"page":"284-298","source":"Crossref","is-referenced-by-count":52,"title":["Scene Semantics from Long-Term Observation of People"],"prefix":"10.1007","author":[{"given":"Vincent","family":"Delaitre","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David F.","family":"Fouhey","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"}]},{"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"}]}],"member":"297","reference":[{"key":"21_CR1","volume-title":"Vision science: photons to phenomenology","author":"S.E. Palmer","year":"1999","unstructured":"Palmer, S.E.: Vision science: photons to phenomenology. MIT Press, Cambridge (1999)"},{"key":"21_CR2","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":"21_CR3","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-008-0202-0","volume":"82","author":"P. Kohli","year":"2009","unstructured":"Kohli, P., Ladicky, L., Torr, P.: Robust higher order potentials for enforcing label consistency. IJCV\u00a082, 302\u2013324 (2009)","journal-title":"IJCV"},{"key":"21_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11744023_1","volume-title":"Computer Vision \u2013 ECCV 2006","author":"J. Shotton","year":"2006","unstructured":"Shotton, J., Winn, J., Rother, C., Criminisi, A.: TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol.\u00a03951, pp. 1\u201315. Springer, Heidelberg (2006)"},{"key":"21_CR5","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":"21_CR6","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":"21_CR7","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-642-33715-4_53","volume-title":"ECCV 2012","author":"D.F. Fouhey","year":"2012","unstructured":"Fouhey, D.F., Delaitre, V., Gupta, A., Efros, A.A., Laptev, I., Sivic, J.: People Watching: Human Actions as a Cue for Single View Geometry. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol.\u00a07576, pp. 732\u2013745. Springer, Heidelberg (2012)"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: Using spatial and functional compatibility for recognition. PAMI (2009)","DOI":"10.1109\/TPAMI.2009.83"},{"key":"21_CR9","unstructured":"Delaitre, V., Sivic, J., Laptev, I.: Learning person-object interactions for action recognition in still images. In: NIPS (2011)"},{"key":"21_CR10","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":"21_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-3-540-79547-6_42","volume-title":"Computer Vision Systems","author":"M. Stark","year":"2008","unstructured":"Stark, M., Lies, P., Zillich, M., Wyatt, J., Schiele, B.: Functional Object Class Detection Based on Learned Affordance Cues. In: Gasteratos, A., Vincze, M., Tsotsos, J.K. (eds.) ICVS 2008. LNCS, vol.\u00a05008, pp. 435\u2013444. Springer, Heidelberg (2008)"},{"key":"21_CR12","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":"21_CR13","doi-asserted-by":"crossref","unstructured":"Yao, B., Fei-Fei, L.: Modeling mutual context of object and human pose in human-object interaction activities. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"21_CR14","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":"21_CR15","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":"21_CR16","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. Kjellstr\u00f6m","year":"2008","unstructured":"Kjellstr\u00f6m, H., Romero, J., Mart\u00ednez, D., Kragi\u0107, 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":"21_CR17","doi-asserted-by":"crossref","unstructured":"Fathi, A., Ren, X., Rehg, J.: Learning to recognize objects in egocentric activities. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Peursum, P., West, G., Venkatesh, S.: Combining image regions and human activity for indirect object recognition in indoor wide-angle views. In: ICCV (2005)","DOI":"10.1109\/ICCV.2005.57"},{"key":"21_CR19","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.W. Turek","year":"2010","unstructured":"Turek, M.W., 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":"21_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/11744078_9","volume-title":"Computer Vision \u2013 ECCV 2006","author":"X. Wang","year":"2006","unstructured":"Wang, X., Tieu, K., Grimson, E.: Learning Semantic Scene Models by Trajectory Analysis. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part III. LNCS, vol.\u00a03953, pp. 110\u2013123. Springer, Heidelberg (2006)"},{"key":"21_CR21","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":"21_CR22","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":"21_CR23","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":"21_CR24","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":"21_CR25","doi-asserted-by":"crossref","unstructured":"Rodriguez, M., Laptev, I., Sivic, J., Audibert, J.Y.: Density-aware person detection and tracking in crowds. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126526"},{"key":"21_CR26","unstructured":"Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: WS-SLCV, ECCV (2004)"},{"key":"21_CR27","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D. Lowe","year":"2004","unstructured":"Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV\u00a060, 91\u2013110 (2004)","journal-title":"IJCV"},{"key":"21_CR28","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":"21_CR29","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"P. Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV\u00a059, 167\u2013181 (2004)","journal-title":"IJCV"},{"key":"21_CR30","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning. Springer (2003)"},{"key":"21_CR31","unstructured":"Staufer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: CVPR (1998)"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Ferrari, V., Marin-Jimenez, M., Zisserman, A.: Progressive search space reduction for human pose estimation. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587468"},{"key":"21_CR33","doi-asserted-by":"publisher","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.: Object detection with discriminatively trained part based models. PAMI\u00a032, 1627\u20131645 (2010)","journal-title":"PAMI"}],"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\/978-3-642-33783-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T16:28:49Z","timestamp":1643473729000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33783-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642337826","9783642337833"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33783-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}