Synergy and Synchrony in Couple Dances

TL;DR

This paper demonstrates that incorporating social interaction data significantly improves the prediction and synthesis of couple dance movements, highlighting the importance of social cues in motion modeling.

Contribution

It introduces a new in-the-wild Swing dance dataset and shows the benefits of socially conditioned motion prediction over single-person models.

Findings

Socially conditioned models outperform individual motion prediction.

Interaction-aware models produce more realistic dance synthesis.

Single-person prediction is notably challenging in this context.

Abstract

This paper asks to what extent social interaction influences one's behavior. We study this in the setting of two dancers dancing as a couple. We first consider a baseline in which we predict a dancer's future moves conditioned only on their past motion without regard to their partner. We then investigate the advantage of taking social information into account by conditioning also on the motion of their dancing partner. We focus our analysis on Swing, a dance genre with tight physical coupling for which we present an in-the-wild video dataset. We demonstrate that single-person future motion prediction in this context is challenging. Instead, we observe that prediction greatly benefits from considering the interaction partners' behavior, resulting in surprisingly compelling couple dance synthesis results (see supp. video). Our contributions are a demonstration of the advantages of socially conditioned future motion prediction and an in-the-wild, couple dance video dataset to enable future research in this direction. Video results are available on the project website: https://von31.github.io/synNsync