A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionSkeleton Based Action RecognitionSimilar Papers 제목 키워드 기반
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjace…
Action RecognitionSkeleton Based Action RecognitionTemporal Decoupling Graph Convolutional Network for Skeleton-based Gesture Recognition
Skeleton-based gesture recognition methods have achieved high success using Graph Convolutional Network (GCN), which commonly uses an adjacency matrix to model the spatial topology of skeletons. However, previous methods…
Gesture RecognitionHand Gesture RecognitionSkeleton Based Action RecognitionSkeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network
In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most exist…
Action RecognitionImage DescriptionSkeleton Based Action RecognitionTemporal Action LocalizationPGCN-TCA: Pseudo Graph Convolutional Network With Temporal and Channel-Wise Attention for Skeleton-Based Action Recognition
Skeleton-based human action recognition has become an active research area in recent years. The key to this task is to fully explore both spatial and temporal features. Recently, GCN-based methods modeling the human body…
Action RecognitionSkeleton Based Action RecognitionTemporal Action LocalizationBlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
Graph Convolutional Networks (GCNs) have long set the state-of-the-art in skeleton-based action recognition leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacen…
Action RecognitionSkeleton Based Action Recognition