Dynamical binary latent variable models for 3D human pose tracking

@article{Taylor2010DynamicalBL,
  title={Dynamical binary latent variable models for 3D human pose tracking},
  author={Graham W. Taylor and Leonid Sigal and David J. Fleet and Geoffrey E. Hinton},
  journal={2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
  year={2010},
  pages={631-638}
}
We introduce a new class of probabilistic latent variable model called the Implicit Mixture of Conditional Restricted Boltzmann Machines (imCRBM) for use in human pose tracking. Key properties of the imCRBM are as follows: (1) learning is linear in the number of training exemplars so it can be learned from large datasets; (2) it learns coherent models of… CONTINUE READING

9 Figures & Tables

Topics

Statistics

010203020082009201020112012201320142015201620172018
Citations per Year

147 Citations

Semantic Scholar estimates that this publication has 147 citations based on the available data.

See our FAQ for additional information.