Research Projects

Topologically-Constrained Latent Variable Models

*** THIS PROJECT IS NO LONGER ACTIVE ***

Trevor Darrell, Raquel Urtasun¹, David Fleet, Andreas Gieger², Jovan Popovic³ and Neil Lawrence⁴

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 data we expect latent spaces that are cylindrical or a toroidal, that are poorly captured with a Euclidean space. In this paper, we present a range of approaches for embedding data in a non-Euclidean latent space. Our focus is the Gaussian Process latent variable model. In the context of human motion modeling this allows us to (a) learn models with interpretable latent directions enabling, for example, style/content separation, and (b) generalise beyond the data set enabling us to learn transitions between motion styles even though such transitions are not present in the data

[1]

R. Urtasun, D. J. Fleet, A. Geiger, J. Popovic, T. Darrell and N. D. Lawrence., Topologically-Constrained Latent Variable Models. ICML 2008

¹ICSI
²TU Karlsruhe
³Adobe
⁴U. Manchester