AFAR: A Deep Learning Based Tool for Automated Facial Affect Recognition - Robotics Institute Carnegie Mellon University

AFAR: A Deep Learning Based Tool for Automated Facial Affect Recognition

Itir Onal Ertugrul, Laszlo A. Jeni, Wanqiao Ding, and Jeffrey F. Cohn
Conference Paper, Proceedings of 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG '19), May, 2019

Abstract

Automated facial affect recognition is crucial to multiple domains (e.g., health, education, entertainment). Commercial tools are available but costly and of unknown validity. Opensource ones [1] lack user-friendly GUI for use by nonprogrammers. For both types, evidence of domain transfer and options for retraining for use in new domains typically are lacking. Deep approaches have two key advantages. They typically outperform shallow ones for facial affect recognition [2], [3], [4]. And pre-trained models provided by deep approaches can be fine tuned with new datasets to optimize performance. We demo AFAR1: an open-source, deep-learning based, user-friendly tool for automated facial affect recognition.

BibTeX

@conference{Ertugrul-2019-119658,
author = {Itir Onal Ertugrul and Laszlo A. Jeni and Wanqiao Ding and Jeffrey F. Cohn},
title = {AFAR: A Deep Learning Based Tool for Automated Facial Affect Recognition},
booktitle = {Proceedings of 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG '19)},
year = {2019},
month = {May},
}