Priors for people tracking from small training sets

  • Urtasun R
  • Fleet D
  • Hertzmann A
 et al. 
  • 107


    Mendeley users who have this article in their library.
  • 181


    Citations of this article.


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 low-dimensional embedding of the high-dimensional pose data and a density function that both gives higher probability to points close to training data and provides a nonlinear probabilistic mapping from the low-dimensional latent space to the full-dimensional pose space. The SGPLVM is a natural choice when only small amounts of training data are available. We demonstrate our approach with two distinct motions, golfing and walking. We show that the SGPLVM sufficiently constrains the problem such that tracking can be accomplished with straightforward deterministic optimization.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text


  • Raquel Urtasun

  • David J. Fleet

  • Aaron Hertzmann

  • Pascal Fua

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free