Automatic Visual Mimicry Expression Analysis in Interpersonal Interaction

Abstract

Mimicry occurs in conversations both when people agree with each other and when they do not. However, it has been reported that there is more mimicry when people agree than when they disagree: when people want to express shared opinions and attitudes, they do so by displaying behavior that is similar to their interlocutors' behavior. In a conversation, mimicry occurs in order to gain acceptance from an interaction partner by conforming to that person's attitudes, opinions, and behavior. In this paper we describe how visual behavioral information expressed between two interlocutors can be used to detect and identify visual mimicry. We extract and encode visual features that are expected to represent mimicry in a useful way. In order to show that mimicry has indeed occurred, we calculate correlations between visual features extracted from the interactants and compare these against each other and against a baseline. We show that it is possible to visualize the occurrence of visual mimicry during the progress of a conversation which allows us to research in which situations and to what extent mimicry occurs.