000220616 001__ 220616
000220616 005__ 20190317000510.0
000220616 037__ $$aCONF
000220616 245__ $$aStructured Prediction of 3D Human Pose with Deep Neural Networks
000220616 269__ $$a2016
000220616 260__ $$c2016
000220616 336__ $$aConference Papers
000220616 520__ $$aMost recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 3D pose, which ignores the dependencies between human joints, or model these dependencies via a max-margin structured learning framework, which involves a high computational cost at inference time. In this paper, we introduce a Deep Learning regression architecture for structured prediction of 3D human pose from monocular images that relies on an overcomplete autoencoder to learn a high-dimensional latent pose representation and account for joint dependencies. We demonstrate that our approach outperforms state-of-the-art ones both in terms of structure preservation and prediction accuracy.
000220616 6531_ $$aStructured prediction
000220616 6531_ $$aDeep learning
000220616 6531_ $$a3D human pose estimation
000220616 700__ $$0247609$$g211045$$aTekin, Bugra
000220616 700__ $$0250305$$g245069$$aKatircioglu, Isinsu
000220616 700__ $$0(EPFLAUTH)119864$$g119864$$aSalzmann, Mathieu
000220616 700__ $$aLepetit, Vincent$$g149007$$0240235
000220616 700__ $$aFua, Pascal$$g112366$$0240252
000220616 7112_ $$dSeptember 19-22, 2016$$cYork, UK$$aBritish Machine Vision Conference (BMVC)
000220616 8564_ $$uhttps://infoscience.epfl.ch/record/220616/files/tekin_bmvc16.pdf$$zn/a$$s818961$$yn/a
000220616 8564_ $$uhttps://infoscience.epfl.ch/record/220616/files/tekin_bmvc16_abstract.pdf$$zn/a$$s308862
000220616 909C0 $$xU10659$$0252087$$pCVLAB
000220616 909CO $$qGLOBAL_SET$$pconf$$ooai:infoscience.tind.io:220616$$pIC
000220616 917Z8 $$x211045
000220616 917Z8 $$x112366
000220616 917Z8 $$x112366
000220616 937__ $$aEPFL-CONF-220616
000220616 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000220616 980__ $$aCONF