About this Research Topic
The dynamics of both perception and behavior-changing overtime for all the agents pose a difficult problem, for both those who want to investigate it and for those who aim at modeling it in computational solutions. The temporal perceptual inference demands high coordination between the context of the interaction, what is expressed, and what activities were planned by both partners.
Most of the current research on modeling affective behavior disregards the issue of considering such dynamic shared perception. Current approaches often ground their contribution in pre-trained learning models, which are purely data-driven, or in reproducing existing human behavior into computational models. Such methods allow for easily reproducible solutions, but also often limit the generalizability of the results and impact to specific and relatively simple situations.
Understanding shared perception as part of affective processing will allow us to tackle this problem and to provide the next step towards a real-world affective computing system. The goal of this research topic is to present and discuss new findings, theories, systems, and trends in affective shared perception and computational models.
We are interested in collecting interesting and exciting research from researchers on the areas of social cognition, affective computing, and human-robot interaction, including also, but not restricted to specialists in computer and cognitive science, psychologists, neuroscientists, and specialists in bio-inspired solutions. We envision that it will allow us to tackle the existing problems in this area and it will provide the next step towards a real-world affective computing system.
Keywords: Affective Computing, Perception, Shared Perception, Developmental Learning, Machine Learning
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.