We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a...
Raquel Urtasun, David J. Fleet, Aaron Hertzmann, P...
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...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
We propose a novel nonlinear, probabilistic and variational method for adding shape information to level setbased segmentation and tracking. Unlike previous work, we represent sha...
In dimensionality reduction approaches, the data are typically embedded in a Euclidean latent space. However for some data sets this is inappropriate. For example, in human motion...
Raquel Urtasun, David J. Fleet, Andreas Geiger, Jo...