Using Hankel Matrices for Dynamics-Based Facial Emotion Recognition and Pain Detection

Abstract

This paper proposes a new approach to model the temporal dynamics of a sequence of facial expressions. To this purpose, a sequence of Face Image Descriptors (FID) is regarded as the output of a Linear Time Invariant (LTI) system. The temporal dynamics of such sequence of descriptors are represented by means of a Hankel matrix. The paper presents different strategies to compute dynamics-based representation of a sequence of FID, and reports classification accuracy values of the proposed representations within different standard classification frameworks. The representations have been validated in two very challenging application domains: emotion recognition and pain detection. Experiments on two publicly available benchmarks and comparison with state-of-the-art approaches demonstrate that the dynamics-based FID representation attains competitive performance when off-the-shelf classification tools are adopted.

Cite

Text

Presti and La Cascia. "Using Hankel Matrices for Dynamics-Based Facial Emotion Recognition and Pain Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301351

Markdown

[Presti and La Cascia. "Using Hankel Matrices for Dynamics-Based Facial Emotion Recognition and Pain Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/presti2015cvprw-using/) doi:10.1109/CVPRW.2015.7301351

BibTeX

@inproceedings{presti2015cvprw-using,
  title     = {{Using Hankel Matrices for Dynamics-Based Facial Emotion Recognition and Pain Detection}},
  author    = {Presti, Liliana Lo and La Cascia, Marco},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2015},
  pages     = {26-33},
  doi       = {10.1109/CVPRW.2015.7301351},
  url       = {https://mlanthology.org/cvprw/2015/presti2015cvprw-using/}
}