English

Facial Expression Editing with Continuous Emotion Labels

Computer Vision and Pattern Recognition 2020-06-23 v1 Machine Learning Image and Video Processing

Abstract

Recently deep generative models have achieved impressive results in the field of automated facial expression editing. However, the approaches presented so far presume a discrete representation of human emotions and are therefore limited in the modelling of non-discrete emotional expressions. To overcome this limitation, we explore how continuous emotion representations can be used to control automated expression editing. We propose a deep generative model that can be used to manipulate facial expressions in facial images according to continuous two-dimensional emotion labels. One dimension represents an emotion's valence, the other represents its degree of arousal. We demonstrate the functionality of our model with a quantitative analysis using classifier networks as well as with a qualitative analysis.

Keywords

Cite

@article{arxiv.2006.12210,
  title  = {Facial Expression Editing with Continuous Emotion Labels},
  author = {Alexandra Lindt and Pablo Barros and Henrique Siqueira and Stefan Wermter},
  journal= {arXiv preprint arXiv:2006.12210},
  year   = {2020}
}

Comments

8 pages, 5 figures. 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), May 2019

R2 v1 2026-06-23T16:31:05.789Z