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.
Ranked #5 on Facial Action Unit Detection on BP4D