Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines

Abstract

We present a type of Temporal Restricted Boltzmann Machine that defines a probability distribution over an output sequence conditional on an input sequence. It shares the desirable properties of RBMs: efficient exact inference, an exponentially more expressive latent state than HMMs, and the ability to model nonlinear structure and dynamics. We apply our model to a challenging real-world graphics problem: facial expression transfer. Our results demonstrate improved performance over several baselines modeling high-dimensional 2D and 3D data.

Cite

Text

Zeiler et al. "Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines." Neural Information Processing Systems, 2011.

Markdown

[Zeiler et al. "Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines." Neural Information Processing Systems, 2011.](https://mlanthology.org/neurips/2011/zeiler2011neurips-facial/)

BibTeX

@inproceedings{zeiler2011neurips-facial,
  title     = {{Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines}},
  author    = {Zeiler, Matthew D. and Taylor, Graham W. and Sigal, Leonid and Matthews, Iain and Fergus, Rob},
  booktitle = {Neural Information Processing Systems},
  year      = {2011},
  pages     = {1629-1637},
  url       = {https://mlanthology.org/neurips/2011/zeiler2011neurips-facial/}
}