The Many Moods of Emotion - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

The Many Moods of Emotion

Abstract

This paper presents a novel approach to the facial expression generation problem. Building upon the assumption of the psychological community that emotion is intrinsically continuous, we first design our own continuous emotion representation with a 3-dimensional latent space issued from a neural network trained on discrete emotion classification. The so-obtained representation can be used to annotate large in the wild datasets and later used to trained a Generative Adversarial Network. We first show that our model is able to map back to discrete emotion classes with a objectively and subjectively better quality of the images than usual discrete approaches. But also that we are able to pave the larger space of possible facial expressions, generating the many moods of emotion. Moreover, two axis in this space may be found to generate similar expression changes as in traditional continuous representations such as arousal-valence. Finally we show from visual interpretation, that the third remaining dimension is highly related to the well-known dominance dimension from psychology.
Fichier principal
Vignette du fichier
main.pdf (4.63 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01908390 , version 1 (31-10-2018)

Identifiers

Cite

Valentin Vielzeuf, Corentin Kervadec, Stéphane Pateux, Frédéric Jurie. The Many Moods of Emotion. 2018. ⟨hal-01908390⟩
182 View
104 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More