Correlation and Interpolation Networks for Real-Time Expression Analysis/Synthesis

Abstract

We describe a framework for real-time tracking of facial expressions that uses neurally-inspired correlation and interpolation methods. A distributed view-based representation is used to characterize facial state, and is computed using a replicated correlation network. The ensemble response of the set of view correlation scores is input to a network based interpolation method, which maps perceptual state to motor control states for a simulated 3-D face model. Activation levels of the motor state correspond to muscle activations in an anatomically derived model. By integrating fast and robust 2-D processing with 3-D models, we obtain a system that is able to quickly track and interpret complex facial motions in real-time.

Cite

Text

Darrell et al. "Correlation and Interpolation Networks for Real-Time Expression Analysis/Synthesis." Neural Information Processing Systems, 1994.

Markdown

[Darrell et al. "Correlation and Interpolation Networks for Real-Time Expression Analysis/Synthesis." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/darrell1994neurips-correlation/)

BibTeX

@inproceedings{darrell1994neurips-correlation,
  title     = {{Correlation and Interpolation Networks for Real-Time Expression Analysis/Synthesis}},
  author    = {Darrell, Trevor and Essa, Irfan A. and Pentland, Alex},
  booktitle = {Neural Information Processing Systems},
  year      = {1994},
  pages     = {909-916},
  url       = {https://mlanthology.org/neurips/1994/darrell1994neurips-correlation/}
}