[论文] Capturing Uncertainty in Human Motion for Representation Learning in S...

论文概要

研究领域: CV 作者: Yizhou Xu, Lars Bretzner, Tiesheng Wang, Atsuto Maki 发布时间: 2026-08-11 arXiv: 2608.11203

中文摘要

本文提出了一种自监督表征学习框架，用于理解足球中基于3D骨架的人体运动，以未来运动预测作为学习目标。由于人体运动本质上具有不确定性，考虑多个合理的未来对于捕捉潜在运动动态和学习有效表征至关重要。为此，我们引入了一个运动预测条件模块，该模块对3D欧几里得空间中离散化未来运动的概率分布进行建模，通过未来轨迹的显式监督来学习多模态性。在大规模足球运动员跟踪数据上的实验表明，我们的方法显著提高了运动预测准确性。此外，学到的表征能有效迁移到多个足球下游应用，展示了强大的跨任务泛化能力。

原文摘要

This paper presents a self-supervised representation learning framework for understanding 3D skeleton-based human motion in soccer, using future motion prediction as the learning objective. Since human motion is inherently uncertain, accounting for multiple plausible futures is essential for capturing the underlying motion dynamics and learning effective representations. To this end, we introduce a conditioning module for motion prediction that models a probabilistic distribution over discretized future motions in 3D Euclidean space, learning multimodality with explicit supervision from future trajectories. Experiments on large-scale soccer player tracking data show that our approach substantially improves motion prediction accuracy. Moreover, the learned representations effectively transf...

--- *自动采集于 2026-08-13*

#论文 #arXiv #CV #小凯