Joint relation modeling is a curial component in human motion prediction. Most existing methods rely on skeletal-based graphs to build the joint relations, where local interactive relations between joint pairs are well learned. However, the motion coordination, a global joint relation reflecting the simultaneous cooperation of all joints, is usually weakened because it is learned from part to whole progressively and asynchronously. Thus, the final predicted motions usually appear unrealistic. To tackle this issue, we learn a medium, called coordination attractor (CA), from the spatiotemporal features of motion to characterize the global motion features, which is subsequently used to build new relative joint relations. Through the CA, all joints are related simultaneously, and thus the motion coordination of all joints can be better learned. Based on this, we further propose a novel joint relation modeling module, Comprehensive Joint Relation Extractor (CJRE), to combine this motion coordination with the local interactions between joint pairs in a unified manner. Additionally, we also present a Multi-timescale Dynamics Extractor (MTDE) to extract enriched dynamics from the raw position information for effective prediction. Extensive experiments show that the proposed framework outperforms state-of-the-art methods in both short- and long-term predictions on H3.6M, CMU-Mocap, and 3DPW.

翻译：关节关系建模是人体运动预测中的关键组成部分。现有方法大多依赖基于骨骼的图来构建关节关系，其中关节对之间的局部交互关系得以充分学习。然而，运动协调性——反映所有关节同步协作的全局关节关系——通常被弱化，因为它是从局部到整体逐渐且异步地学习的。因此，最终预测的运动往往显得不真实。为解决这一问题，我们从运动的时空特征中学习一种称为协调吸引子（CA）的中介，以表征全局运动特征，并随后用于构建新的相对关节关系。通过CA，所有关节同时关联，从而能更好地学习所有关节的运动协调性。在此基础上，我们进一步提出一种新颖的关节关系建模模块——综合关节关系提取器（CJRE），以将这种运动协调性与关节对间的局部交互统一结合。此外，我们还提出了多时间尺度动态提取器（MTDE），从原始位置信息中提取丰富的动态特征以实现有效预测。大量实验表明，所提框架在H3.6M、CMU-Mocap和3DPW数据集上的短时与长时预测中均优于现有最优方法。