{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:58:19Z","timestamp":1781283499738,"version":"3.54.1"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1109\/iccv.2007.4408828","type":"proceedings-article","created":{"date-parts":[[2008,1,4]],"date-time":"2008-01-04T15:34:53Z","timestamp":1199460893000},"page":"1-8","source":"Crossref","is-referenced-by-count":139,"title":["Learning 3-D Scene Structure from a Single Still Image"],"prefix":"10.1109","author":[{"given":"Ashutosh","family":"Saxena","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew Y.","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Multi viewpoint stereo from uncalibrated video sequences","author":"koch","year":"1998","journal-title":"ECCV"},{"key":"ref11","article-title":"Multi-conditional learning: generative\/discriminative training for clustering and classification","author":"mccalloum","year":"2006","journal-title":"AAAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102426"},{"key":"ref13","article-title":"Learning depth from single monocular images","volume":"18","author":"saxena","year":"2005","journal-title":"NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0071-y"},{"key":"ref15","article-title":"Depth estimation using monocular and stereo cues","author":"saxena","year":"2007","journal-title":"IJCAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014573219977"},{"key":"ref17","author":"wandell","year":"1995","journal-title":"Foundations of Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/34.784284"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.23"},{"key":"ref3","article-title":"Automatic single-image 3d reconstructions of indoor manhattan world scenes","author":"delage","year":"2005","journal-title":"ISRR"},{"key":"ref6","author":"forsyth","year":"2003","journal-title":"Computer Vision A Modern Approach"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073232"},{"key":"ref2","article-title":"Histogram of oriented gradients for human detection","author":"dalai","year":"2005","journal-title":"CVPR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026598000963"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.107"}],"event":{"name":"2007 IEEE 11th International Conference on Computer Vision","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2007,10,14]]},"end":{"date-parts":[[2007,10,21]]}},"container-title":["2007 IEEE 11th International Conference on Computer Vision"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4408818\/4408819\/04408828.pdf?arnumber=4408828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:14:02Z","timestamp":1781280842000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4408828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/iccv.2007.4408828","relation":{},"subject":[],"published":{"date-parts":[[2007]]}}}