论文标题
基于GCN的基于GCN的模型中的新邻接矩阵配置，用于基于骨架的动作识别
A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition
论文作者
论文摘要
人类骨骼数据由于其背景鲁棒性和高效率而受到行动识别的越来越多。在基于骨架的动作识别中，图形卷积网络（GCN）已成为主流方法。本文分析了基于GCN的模型的基本因素 - 邻接矩阵。我们注意到，大多数基于GCN的方法基于人类天然骨架结构进行其邻接矩阵。根据我们以前的工作和分析，我们建议人类的自然骨骼结构邻接矩阵不适合基于骨架的动作识别。我们提出了一个新的邻接矩阵，该矩阵放弃了所有僵化的邻居连接，但该模型可以自适应地学习关节的关系。我们对两个基于骨架的动作识别数据集（NTURGBD60和FINEGYM）进行了验证模型进行广泛的实验和分析。全面的实验结果和分析表明，1）最广泛使用的人类天然骨骼结构邻接矩阵在基于骨架的动作识别中不适合； 2）所提出的邻接矩阵在模型性能，噪声鲁棒性和可传递性方面表现出色。
Human skeleton data has received increasing attention in action recognition due to its background robustness and high efficiency. In skeleton-based action recognition, graph convolutional network (GCN) has become the mainstream method. This paper analyzes the fundamental factor for GCN-based models -- the adjacency matrix. We notice that most GCN-based methods conduct their adjacency matrix based on the human natural skeleton structure. Based on our former work and analysis, we propose that the human natural skeleton structure adjacency matrix is not proper for skeleton-based action recognition. We propose a new adjacency matrix that abandons all rigid neighbor connections but lets the model adaptively learn the relationships of joints. We conduct extensive experiments and analysis with a validation model on two skeleton-based action recognition datasets (NTURGBD60 and FineGYM). Comprehensive experimental results and analysis reveals that 1) the most widely used human natural skeleton structure adjacency matrix is unsuitable in skeleton-based action recognition; 2) The proposed adjacency matrix is superior in model performance, noise robustness and transferability.
