Constrained by the lack of model interpretability and a deep understanding of human movement in traditional movement recognition machine learning methods, this study introduces a novel representation learning method based on causal inference to better understand human joint dynamics and complex behaviors. We propose a two-stage framework that combines the Peter-Clark (PC) algorithm and Kullback-Leibler (KL) divergence to identify and quantify causal relationships between joints. Our method effectively captures interactions and produces interpretable, robust representations. Experiments on the EmoPain dataset show that our causal GCN outperforms traditional GCNs in accuracy, F1 score, and recall, especially in detecting protective behaviors. The model is also highly invariant to data scale changes, enhancing its reliability in practical applications. Our approach advances human motion analysis and paves the way for more adaptive intelligent healthcare solutions.

翻译：受限于传统动作识别机器学习方法缺乏模型可解释性以及对人体运动的深层理解，本研究引入一种基于因果推断的新型表征学习方法，以更好地理解人体关节动力学与复杂行为。我们提出一个两阶段框架，结合 Peter-Clark (PC) 算法与 Kullback-Leibler (KL) 散度来识别并量化关节间的因果关系。该方法能有效捕捉交互作用，并生成可解释、鲁棒的表征。在 EmoPain 数据集上的实验表明，我们的因果 GCN 在准确率、F1 分数与召回率上均优于传统 GCN，尤其在检测保护性行为方面表现突出。该模型对数据尺度变化亦具有高度不变性，从而提升了其在实际应用中的可靠性。我们的方法推动了人体运动分析的发展，并为更具适应性的智能医疗解决方案开辟了道路。