{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:49:40Z","timestamp":1782406180455,"version":"3.54.5"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Canadian NSERC Discovery"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2019,4,1]]},"DOI":"10.1109\/tpami.2018.2816031","type":"journal-article","created":{"date-parts":[[2018,3,15]],"date-time":"2018-03-15T20:46:05Z","timestamp":1521146765000},"page":"901-914","source":"Crossref","is-referenced-by-count":153,"title":["MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1926-5597","authenticated-orcid":false,"given":"Xiaowei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menglong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Pavlakos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spyridon","family":"Leonardos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos G.","family":"Derpanis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0498-0758","authenticated-orcid":false,"given":"Kostas","family":"Daniilidis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.464"},{"key":"ref72","first-page":"32","article-title":"Human pose estimation in space and time using 3D CNN","author":"grinciunaite","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref70","first-page":"1455","article-title":"Manopt, a Matlab toolbox for optimization on manifolds","volume":"15","author":"boumal","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref39","first-page":"332","article-title":"3D human pose estimation from monocular images with deep convolutional neural network","author":"li","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref38","article-title":"Depth sweep regression forests for estimating 3D human pose from images","author":"kostrikov","year":"2014","journal-title":"Proc British Mach Vis Conf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.21"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.535"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.414"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.149"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.467"},{"key":"ref35","first-page":"2065","article-title":"Implicitly constrained Gaussian process regression for monocular non-rigid pose estimation","author":"salzmann","year":"2010","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0204-y"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.303"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.466"},{"key":"ref63","first-page":"1381","article-title":"Estimating human shape and pose from a single image","author":"guan","year":"2009","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0493-4"},{"key":"ref64","first-page":"561","article-title":"Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image","author":"bogo","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211339"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0293-2"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5244\/C.27.48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238424"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.537"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1006\/cviu.1995.1004","article-title":"Active shape models–Their training and application","volume":"61","author":"cootes","year":"1995","journal-title":"Comput Vis Image Understanding"},{"key":"ref69","article-title":"Gradient methods for minimizing composite objective function","author":"nesterov","year":"2007"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/0734-189X(85)90094-5","article-title":"Determination of 3D human body postures from a single view","volume":"30","author":"lee","year":"1985","journal-title":"Comput Vis Graph Image Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"ref20","first-page":"1799","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","author":"tompson","year":"2014","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.302"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995607"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.222"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301337"},{"key":"ref26","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.233"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0860-7"},{"key":"ref51","first-page":"467","article-title":"Deterministic 3D human pose estimation using rigid structure","author":"valmadre","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247988"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2605097"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299074"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"ref55","first-page":"174","article-title":"Pose locality constrained representation for 3D human pose reconstruction","author":"fan","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487183"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.237"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126243"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540156"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.326"},{"key":"ref12","first-page":"62","article-title":"Spatio-temporal matching for human detection in video","author":"zhou","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.08.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2006.3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-93808-0_3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-997-0_11"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2016.09.002","article-title":"3D human pose estimation: A review of the literature and analysis of covariates","volume":"152","author":"sarafianos","year":"2016","journal-title":"Comput Vis Image Understanding"},{"key":"ref18","first-page":"1736","article-title":"Articulated pose estimation by a graphical model with image dependent pairwise relations","author":"chen","year":"2014","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref19","article-title":"Learning human pose estimation features with convolutional networks","author":"jain","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2000.854941"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.2000.0878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698581"},{"key":"ref5","first-page":"573","article-title":"Reconstructing 3D human pose from 2D image landmarks","author":"ramakrishna","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.200"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"ref9","first-page":"1293","article-title":"Joint action recognition and pose estimation from video","author":"xiaohan nie","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref46","first-page":"3108","article-title":"MoCap-guided data augmentation for 3D pose estimation in the wild","author":"rogez","year":"2016","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.58"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0684-2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.201"},{"key":"ref42","first-page":"20","article-title":"Marker-less 3D human motion capture with monocular image sequence and height-maps","author":"du","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.113"},{"key":"ref44","first-page":"186","article-title":"Deep kinematic pose regression","author":"zhou","year":"2016","journal-title":"Proc European Conf Comp Vis Workshop"},{"key":"ref43","first-page":"156","article-title":"3D human pose estimation using convolutional neural networks with 2D pose information","author":"park","year":"2016","journal-title":"Proc European Conf Comp Vis Workshop"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8660600\/08316924.pdf?arnumber=8316924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:25Z","timestamp":1657746565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8316924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,1]]},"references-count":73,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2816031","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,1]]}}}