In skeleton-based action recognition, graph convolutional networks (GCNs), which model human body skeletons using graphical components such as nodes and connections, have recently achieved remarkable performance. While the current state-of-the-art methods for skeleton-based action recognition usually assume that completely observed skeletons will be provided, it is problematic to realize this assumption in real-world scenarios since the captured skeletons may be incomplete or noisy. In this work, we propose a skeleton-based action recognition method that is robust to noise interference for the given skeleton features. The key insight of our approach is to train a model by maximizing the mutual information between normal and noisy skeletons using predictive coding in the latent space. We conducted comprehensive skeleton-based action recognition experiments with defective skeletons using the NTU-RGB+D and Kinetics-Skeleton datasets. The experimental results demonstrate that when the skeleton samples are noisy, our approach achieves outstanding performances compared with the existing state-of-the-art methods.

在基于骨骼的动作识别中，使用节点和连接等图形组件对人体骨骼进行建模的图卷积网络 (GCN) 最近取得了显着的性能。虽然当前最先进的基于骨架的动作识别方法通常假设将提供完全观察到的骨架，但在现实世界场景中实现这一假设是有问题的，因为捕获的骨架可能不完整或有噪声。在这项工作中，我们提出了一种基于骨架的动作识别方法，该方法对给定骨架特征的噪声干扰具有鲁棒性。我们方法的关键见解是通过在潜在空间中使用预测编码最大化正常和嘈杂骨架之间的互信息来训练模型。我们使用 NTU-RGB+D 和 Kinetics-Skeleton 数据集对有缺陷的骨骼进行了全面的基于骨骼的动作识别实验。实验结果表明，当骨架样本有噪声时，与现有的最先进方法相比，我们的方法取得了出色的性能。