{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T12:19:22Z","timestamp":1790425162510,"version":"4.1.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2017,2,1]],"date-time":"2017-02-01T00:00:00Z","timestamp":1485907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2017,2]]},"DOI":"10.1109\/tip.2016.2621673","type":"journal-article","created":{"date-parts":[[2016,10,26]],"date-time":"2016-10-26T18:18:21Z","timestamp":1477505901000},"page":"836-846","source":"Crossref","is-referenced-by-count":68,"title":["Exploiting Depth From Single Monocular Images for Object Detection and Semantic Segmentation"],"prefix":"10.1109","volume":"26","author":[{"given":"Yuanzhouhan","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"82","article-title":"Recurrent convolutional neural networks for scene labeling","author":"pinheiro","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.852470"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref32","first-page":"163","article-title":"Deep fisher networks for large-scale image classification","author":"simonyan","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-9794-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298854"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298621"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref27","first-page":"1","article-title":"Visual categorization with bags of keypoints","author":"csurka","year":"2004","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref2","first-page":"634","article-title":"Sliding shapes for 3D object detection in depth images","author":"song","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"ref20","first-page":"182","article-title":"Disparity statistics for pedestrian detection: Combining appearance, motion and stereo","author":"walk","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","first-page":"141","article-title":"A category-level 3D object dataset: Putting the Kinect to work","author":"janoch","year":"2011","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.179"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139363"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref51","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.19"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","first-page":"1161","article-title":"Learning depth from single monocular images","author":"saxena","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0071-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.97"},{"key":"ref16","first-page":"1119","article-title":"Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs","author":"li","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248075"},{"key":"ref18","first-page":"658","article-title":"Depth-encoded Hough voting for joint object detection and shape recovery","author":"sun","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref19","article-title":"Integrating visual and range data for robotic object detection","author":"gould","year":"2008","journal-title":"Proc Eur Conf Comput Vis Workshop Multicamera Multimodal Sensor Fusion"},{"key":"ref4","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095119"},{"key":"ref6","first-page":"224","article-title":"Thinking inside the box: Using appearance models and context based on room geometry","author":"hedau","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","article-title":"Learning depth from single monocular images using deep convolutional neural fields","author":"liu","year":"2015"},{"key":"ref8","first-page":"299","article-title":"Efficient exact inference for 3D indoor scene understanding","author":"schwing","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","first-page":"1288","article-title":"Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces","author":"gupta","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206643"},{"key":"ref46","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref47","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"nathan silberman","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","article-title":"Efficient piecewise training of deep structured models for semantic segmentation","author":"lin","year":"2015"},{"key":"ref41","article-title":"Fully connected deep structured networks","author":"schwing","year":"2015"},{"key":"ref44","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7763897\/07707416.pdf?arnumber=7707416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:12:43Z","timestamp":1642003963000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7707416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2]]},"references-count":53,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tip.2016.2621673","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2]]}}}