{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:08:26Z","timestamp":1761808106977},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Spanish MINECO project RobInstruct","award":["TIN2014-58178-R"],"award-info":[{"award-number":["TIN2014-58178-R"]}]},{"name":"ERA-Net Chistera project I-DRESS","award":["PCIN-2015-147"],"award-info":[{"award-number":["PCIN-2015-147"]}]},{"name":"EU project AEROARMS","award":["H2020-ICT-2014-1-644271"],"award-info":[{"award-number":["H2020-ICT-2014-1-644271"]}]},{"name":"EU project SECOND HANDS","award":["H2020-ICT-2014-1-643950"],"award-info":[{"award-number":["H2020-ICT-2014-1-643950"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1109\/lra.2016.2637444","type":"journal-article","created":{"date-parts":[[2016,12,8]],"date-time":"2016-12-08T19:11:57Z","timestamp":1481224317000},"page":"468-475","source":"Crossref","is-referenced-by-count":25,"title":["Learning Depth-Aware Deep Representations for Robotic Perception"],"prefix":"10.1109","volume":"2","author":[{"given":"Lorenzo","family":"Porzi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel Rota","family":"Bulo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Penate-Sanchez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesc","family":"Moreno-Noguer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"silberman","year":"0","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487265"},{"key":"ref33","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75988-8_28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907778"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298618"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.87"},{"key":"ref36","article-title":"SegNet: A\n Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","author":"badrinarayanan","year":"2015"},{"key":"ref35","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"ref10","first-page":"463","article-title":"Depth and\n height aware semantic RGB-D perception with convolutional neural networks","author":"schulz","year":"0","journal-title":"Proc Eur Symp Artif Neural Netw"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.161"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759657"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref13","first-page":"536","article-title":"Learning 6D object pose estimation using 3D object coordinates","author":"brachmann","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.115"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.231"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref17","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.230"},{"key":"ref19","first-page":"1","article-title":"Indoor semantic segmentation using depth\n information","author":"couprie","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","first-page":"3545","article-title":"Deep networks with internal\n selective attention through feedback connections","author":"stollenga","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139372"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref7","first-page":"345","article-title":"Learning rich features from\n RGB-D images for object detection and segmentation","author":"gupta","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","first-page":"2183","article-title":"Real-time\n 3D scene layout from a single image using convolutional neural networks","author":"yang","year":"0","journal-title":"Proc Int Conf Robot Autom"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353446"},{"key":"ref1","first-page":"2366","article-title":"Depth map\n prediction from a single image using a multi-scale deep network","author":"eigen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.414"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299105"},{"key":"ref24","first-page":"2537","article-title":"Deep symmetry networks","author":"gens","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"584","article-title":"Discriminatively trained sparse code gradients for contour detection","author":"xiaofeng","year":"0","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"ref26","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks\n for visual recognition","author":"he","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.38"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/7797562\/07778240.pdf?arnumber=7778240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:12:06Z","timestamp":1642003926000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7778240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4]]},"references-count":41,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2016.2637444","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4]]}}}