Synthesizing Personality-Dependent Body Postures Using Generative Adversarial Networks

In Personality Computing, one of the major goals is to estimate the personality of an individual by making use of computational techniques. Among the existing models that classify personality traits, the Big-5 factor model is probably the most popular, due to the fact that it provides a compact and complete set of traits describing human personalities. This paper presents an adversarial method that allows the generation of body postures exhibiting the characteristics of a chosen personality trait. The Big-5 and a broader model are analyzed and, in particular, we propose and analyze a technique for generating silhouettes with different levels of extroversion, as well as the aspect of a broader model corresponding to how over (or under) constrained a person is. The proposed approach can be applied in domains such as automatic character animation, marketing, and the broader field of Affective Computing.