37 search results - page 1 / 8 » Dynamical Binary Latent Variable Models for 3D Human Pose Tr... |
CVPR
2010
IEEE
14 years 23 days ago
2010
IEEE
We introduce a new class of probabilistic latent variable model called the Implicit Mixture of Conditional Restricted Boltzmann Machines (imCRBM) for use in human pose tracking. K...
CRV
2008
IEEE
13 years 11 months ago
2008
IEEE
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
ICIP
2007
IEEE
14 years 6 months ago
2007
IEEE
Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. T...
MLMI
2007
Springer
13 years 10 months ago
2007
Springer
We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1]...