Work

Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in a Triadic Interaction

Year: 2019

Type: conference-paper

Abstract: 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.

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr.2019.01113

Authors: Hanbyul Joo, Tomas Simon, Mina Cikara, Yaser Sheikh

Institutions: Meta (United States), Carnegie Mellon University, Harvard University

Language: English

Topic: Human Motion and Animation

Subfield: Control and Systems Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2948091375

FWCI: 16.19

Cites: 82

Cited by: 93

Related to: 10