Affective Facial Expression Processing via Simulation: A Probabilistic Model

TL;DR

This paper introduces a novel probabilistic computational model for affective facial expression processing based on Simulation Theory and mirror-neuron system insights, aiming to improve emotion detection in social AI.

Contribution

It proposes a new probabilistic model that maps facial expressions onto a fixed identity and latent space, inspired by neuroscience, for emotion recognition.

Findings

Preliminary promising results in emotion detection

Probabilistic mapping enhances affective facial expression understanding

Model aligns with neuropsychological theories of mirror neurons

Abstract

Understanding the mental state of other people is an important skill for intelligent agents and robots to operate within social environments. However, the mental processes involved in `mind-reading' are complex. One explanation of such processes is Simulation Theory - it is supported by a large body of neuropsychological research. Yet, determining the best computational model or theory to use in simulation-style emotion detection, is far from being understood. In this work, we use Simulation Theory and neuroscience findings on Mirror-Neuron Systems as the basis for a novel computational model, as a way to handle affective facial expressions. The model is based on a probabilistic mapping of observations from multiple identities onto a single fixed identity (`internal transcoding of external stimuli'), and then onto a latent space (`phenomenological response'). Together with the proposed architecture we present some promising preliminary results