Affective facial expression processing via simulation: A probabilistic model

作者：Vitale Jonathan^*; Williams Mary Anne; Johnston Benjamin; Boccignone Giuseppe

来源：Biologically Inspired Cognitive Architectures, 2014, 10: 30-41.

DOI：10.1016/j.bica.2014.11.005

• Simulation Theory
• Mirror Neurons
• Facial expression
• Latent space
• Probabilistic model

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 %26apos;mind-reading%26apos; 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 (%26apos;internal transcoding of external stimuli%26apos;), and then onto a latent space (%26apos;phenomenological response%26apos;). Together with the proposed architecture we present some promising preliminary results.

• 出版日期2014-10