Multi-View Dynamic Facial Action Unit Detection

1 code implementation • 25 Apr 2017 • Andres Romero, Juan Leon, Pablo Arbelaez

We then move to the novel setup of the FERA 2017 Challenge, in which we propose a multi-view extension of our approach that operates by first predicting the viewpoint from which the video was taken, and then evaluating an ensemble of action unit detectors that were trained for that specific viewpoint.

Action Unit Detection Facial Action Unit Detection