Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset

TL;DR

This paper introduces a large-scale audiovisual dataset and models for understanding and generating dyadic human interactions, advancing socially intelligent AI with applications in virtual agents and multimodal communication.

Contribution

It provides a new extensive dataset and develops models for dyadic motion and facial expression generation aligned with speech, including controllable and multimodal integration capabilities.

Findings

The dataset contains over 4,000 hours of interaction footage from 4,000+ participants.

Models can generate synchronized gestures and facial expressions based on speech and visual cues.

Controllable models can adapt emotional responses and expressivity levels.

Abstract

Human communication involves a complex interplay of verbal and nonverbal signals, essential for conveying meaning and achieving interpersonal goals. To develop socially intelligent AI technologies, it is crucial to develop models that can both comprehend and generate dyadic behavioral dynamics. To this end, we introduce the Seamless Interaction Dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage from over 4,000 participants in diverse contexts. This dataset enables the development of AI technologies that understand dyadic embodied dynamics, unlocking breakthroughs in virtual agents, telepresence experiences, and multimodal content analysis tools. We also develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech. These models can take as input both the speech and visual behavior of their interlocutors. We present a variant with speech from an LLM model and integrations with 2D and 3D rendering methods, bringing us closer to interactive virtual agents. Additionally, we describe controllable variants of our motion models that can adapt emotional responses and expressivity levels, as well as generating more semantically-relevant gestures. Finally, we discuss methods for assessing the quality of these dyadic motion models, which are demonstrating the potential for more intuitive and responsive human-AI interactions.