跳舞时搭档动作对预测至关重要，单人预测难，互动预测更准。
Synergy and Synchrony in Couple Dances
- 基于舞伴动作预测未来动作，比仅用自身历史更有效。
- 在摇摆舞场景中，联合预测误差降低37.6%，合成效果逼真。
- 适合研究人机交互、行为预测与舞蹈生成的学者参考。
本文探讨社会互动如何影响个体行为，以双人舞为研究场景。首先建立基线模型，仅根据舞者自身历史动作预测未来动作；随后引入舞伴运动信息进行联合建模。针对需要紧密身体协作的摇摆舞，我们构建了一个真实环境下的双人舞蹈视频数据集。实验表明，仅依赖个人历史的动作预测效果不佳，而结合舞伴行为后，预测性能显著提升，生成的双人舞蹈序列极具真实性（见补充视频）。本研究展示了社会性条件化未来动作预测的优势，并提供了可用于后续研究的真实世界数据集。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。