Modeling Human Motion Using Binary Latent Variables

We propose a non-linear generative model for human motion data that uses an undirected model with binary latent variables and real-valued "visible" variables that represent joint angles. The latent and visible variables at each time step receive directed connections from the visible variables at the last few time-steps. Such an architecture makes on-line inference efficient and allows us to use a simple approximate learning procedure. After training, the model finds a single set of parameters that simultaneously capture several different kinds of motion. We demonstrate the power of our approach by synthesizing various motion sequences and by performing on-line filling in of data lost during motion capture. Website: http: //www. cs. toronto. edu/gwtaylor/publications/nips2006mhmublv/

Authors

• Graham Taylor University of Guelph
• Geoffrey Hinton
• Sam Roweis

Keywords

No keywords are indexed for this paper.