当前位置:
X-MOL 学术
›
arXiv.cs.LG
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
arXiv - CS - Machine Learning Pub Date : 2020-03-17 , DOI: arxiv-2003.07514 Jongmin Yu, Yongsang Yoon, and Moongu Jeon
arXiv - CS - Machine Learning Pub Date : 2020-03-17 , DOI: arxiv-2003.07514 Jongmin Yu, Yongsang Yoon, and Moongu Jeon
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.
中文翻译:
用于噪声鲁棒的基于骨架的动作识别的预测编码图卷积网络
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。然而,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。在实际场景中应用这个假设可能有问题,因为捕获的骨架总是有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信息具有鲁棒性。我们方法的关键见解是通过使用预测编码方式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基于骨骼的动作识别的综合实验。实验结果表明,与现有的最先进方法相比,我们的方法在对骨架样本进行噪声处理时取得了出色的性能。
更新日期:2020-03-18
中文翻译:
用于噪声鲁棒的基于骨架的动作识别的预测编码图卷积网络
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。然而,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。在实际场景中应用这个假设可能有问题,因为捕获的骨架总是有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信息具有鲁棒性。我们方法的关键见解是通过使用预测编码方式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基于骨骼的动作识别的综合实验。实验结果表明,与现有的最先进方法相比,我们的方法在对骨架样本进行噪声处理时取得了出色的性能。