Large Margin Loss for Learning Facial Movements from Pseudo-Emotions

Andrei Racoviteanu (University Politehnica of Bucharest), Mihai Badea (Image Processing and Analysis Laboratory, University Politehnica of Bucharest), Corneliu Florea (University Politehnica of Bucharest), Laura Florea (University Politehnica of Bucharest), Constantin Vertan (University Politehnica of Bucarest)

Abstract
In this paper we propose a large margin based loss function that enables information transfer from an unsupervised domain to a supervised one. The proposed methodology is applied in the context of face expression analysis. Categorical expressions are easier to understand and mutually exclusive, yet annotation is difficult and arguable. In contrast, facial movements encoded as action units have gained wider acceptance. Our strategy assumes self labeling images in the wild with pseudo-emotions to better learn action units. The proposed method is tested in two challenging scenarios with expressions in the wild, showing improved performance with respect to the baseline.

DOI
10.5244/C.33.99
https://dx.doi.org/10.5244/C.33.99

Files
Paper (PDF)

BibTeX