Computing Spatio-Temporal Representations of Human Faces

Abstract

An approach for analysis and representation of facial dynamics for recognition of facial expressions from image sequences is proposed. The algorithms we develop utilize optical flow computation to identify the direction of rigid and non-rigid motions that are caused by human, facial expressions. A mid-level symbolic representation that is motivated by linguistic and psychological considerations is developed. Recognition of six facial expressions, as well as eye blinking, on a large set of image sequences is reported.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Yacoob and Davis. "Computing Spatio-Temporal Representations of Human Faces." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323812

Markdown

[Yacoob and Davis. "Computing Spatio-Temporal Representations of Human Faces." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/yacoob1994cvpr-computing/) doi:10.1109/CVPR.1994.323812

BibTeX

@inproceedings{yacoob1994cvpr-computing,
  title     = {{Computing Spatio-Temporal Representations of Human Faces}},
  author    = {Yacoob, Yaser and Davis, Larry S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {70-75},
  doi       = {10.1109/CVPR.1994.323812},
  url       = {https://mlanthology.org/cvpr/1994/yacoob1994cvpr-computing/}
}