Dyadic Interaction Modeling for Social Behavior Generation

TL;DR

This paper introduces a novel dyadic interaction modeling framework that jointly learns speaker and listener behaviors to generate realistic 3D facial motions in social interactions, advancing the realism and diversity of generated nonverbal behaviors.

Contribution

The paper presents Dyadic Interaction Modeling (DIM), a pre-training approach using masking and contrastive learning to capture dyadic context for nonverbal behavior generation.

Findings

Outperforms existing methods in generating diverse, realistic listener motions

Establishes new state-of-the-art in motion diversity and realism metrics

Qualitative results show improved expression, eye blinks, and head gestures

Abstract

Human-human communication is like a delicate dance where listeners and speakers concurrently interact to maintain conversational dynamics. Hence, an effective model for generating listener nonverbal behaviors requires understanding the dyadic context and interaction. In this paper, we present an effective framework for creating 3D facial motions in dyadic interactions. Existing work consider a listener as a reactive agent with reflexive behaviors to the speaker's voice and facial motions. The heart of our framework is Dyadic Interaction Modeling (DIM), a pre-training approach that jointly models speakers' and listeners' motions through masking and contrastive learning to learn representations that capture the dyadic context. To enable the generation of non-deterministic behaviors, we encode both listener and speaker motions into discrete latent representations, through VQ-VAE. The pre-trained model is further fine-tuned for motion generation. Extensive experiments demonstrate the superiority of our framework in generating listener motions, establishing a new state-of-the-art according to the quantitative measures capturing the diversity and realism of generated motions. Qualitative results demonstrate the superior capabilities of the proposed approach in generating diverse and realistic expressions, eye blinks and head gestures. The code is available at https://github.com/Boese0601/Dyadic-Interaction-Modeling