Synergy and Synchrony in Couple Dances
This work addresses motion prediction in social interactions for dance analysis, providing a dataset and method that are incremental but useful for research in this domain.
The paper tackles the problem of predicting a dancer's future motion in couple dances, showing that incorporating social interaction with a partner significantly improves prediction accuracy over a baseline that ignores the partner, leading to compelling dance synthesis results.
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