Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?
This addresses the need for automated generation of diverse non-verbal cues in human-computer interaction, representing an incremental advance by extending existing single-reaction methods to multiple reactions.
The paper tackles the problem of generating multiple appropriate facial reactions in dyadic interactions, defining the fMARG task and proposing a framework with new objective evaluation metrics to assess reaction appropriateness.
According to the Stimulus Organism Response (SOR) theory, all human behavioral reactions are stimulated by context, where people will process the received stimulus and produce an appropriate reaction. This implies that in a specific context for a given input stimulus, a person can react differently according to their internal state and other contextual factors. Analogously, in dyadic interactions, humans communicate using verbal and nonverbal cues, where a broad spectrum of listeners' non-verbal reactions might be appropriate for responding to a specific speaker behaviour. There already exists a body of work that investigated the problem of automatically generating an appropriate reaction for a given input. However, none attempted to automatically generate multiple appropriate reactions in the context of dyadic interactions and evaluate the appropriateness of those reactions using objective measures. This paper starts by defining the facial Multiple Appropriate Reaction Generation (fMARG) task for the first time in the literature and proposes a new set of objective evaluation metrics to evaluate the appropriateness of the generated reactions. The paper subsequently introduces a framework to predict, generate, and evaluate multiple appropriate facial reactions.