论文标题
预测编码的基于噪声骨架的动作识别的图形卷积网络
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
论文作者
论文摘要
在基于骨架的动作识别中，图形卷积网络（GCN）使用图形组件（例如节点和连接）对人体骨架进行建模，最近实现了出色的性能。但是，基于骨架的动作识别的当前最新方法通常在提供完全观察到的骨骼的假设上起作用。在实际场景中应用此假设可能是有问题的，因为捕获的骨架总是可能不完整或嘈杂的。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信息具有鲁棒性。我们方法的关键见解是通过使用预测性编码方式来最大化正常骨骼和嘈杂骨骼之间的相互信息来训练模型。我们已经使用NTU-RGB+D和动力学 - 骨骼数据集进行了有关基于骨架的动作识别的全面实验。实验结果表明，与现有的最新方法相比，当骨骼样本噪音时，我们的方法可实现出色的性能。
In skeleton-based action recognition, graph convolutional networks (GCNs), which model human body skeletons using graphical components such as nodes and connections, have achieved remarkable performance recently. However, current state-of-the-art methods for skeleton-based action recognition usually work on the assumption that the completely observed skeletons will be provided. This may be problematic to apply this assumption in real scenarios since there is always a possibility that captured skeletons are incomplete or noisy. In this work, we propose a skeleton-based action recognition method which is robust to noise information of 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 a predictive coding manner. We have conducted comprehensive experiments about skeleton-based action recognition with defected skeletons using NTU-RGB+D and Kinetics-Skeleton datasets. The experimental results demonstrate that our approach achieves outstanding performance when skeleton samples are noised compared with existing state-of-the-art methods.
