Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction
This work addresses the challenge of enabling machines to understand and communicate with humans through nonverbal signals, which is incremental as it builds on existing computational methods with a new dataset and task.
The paper tackles the problem of modeling social interactions for Social AI by formulating a social signal prediction task and introducing a new 3D motion capture dataset of triadic interactions, with baseline methods predicting speaking status, social formation, and body gestures.
We present a new research task and a dataset to understand human social interactions via computational methods, to ultimately endow machines with the ability to encode and decode a broad channel of social signals humans use. This research direction is essential to make a machine that genuinely communicates with humans, which we call Social Artificial Intelligence. We first formulate the "social signal prediction" problem as a way to model the dynamics of social signals exchanged among interacting individuals in a data-driven way. We then present a new 3D motion capture dataset to explore this problem, where the broad spectrum of social signals (3D body, face, and hand motions) are captured in a triadic social interaction scenario. Baseline approaches to predict speaking status, social formation, and body gestures of interacting individuals are presented in the defined social prediction framework.