Published in

Proceedings of the 25th international conference on Machine learning - ICML '08

DOI: 10.1145/1390156.1390292

Links

Tools

Export citation

Search in Google Scholar

Topologically-constrained latent variable models

Proceedings article published in 2008 by Raquel Urtasun, David J. Fleet, Andreas Geiger, Jovan Popovic, Trevor J. Darrell, Neil D. Lawrence ORCID
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Green circle
Preprint: archiving allowed
Upload
Green circle
Postprint: archiving allowed
Upload
Red circle
Published version: archiving forbidden
Policy details
Data provided by SHERPA/RoMEO

Abstract

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 mo- tion data we expect latent spaces that are cylindrical or a toroidal, that are poorly cap- tured with a Euclidean space. In this paper, we present a range of approaches for embed- ding data in a non-Euclidean latent space. Our focus is the Gaussian Process latent vari- able 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.