Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

TL;DR

This paper introduces a dynamic hypergraph convolutional network that adaptively models skeleton data for action recognition, capturing motion information more effectively than traditional fixed-graph methods.

Contribution

The proposed DHGCN employs hypergraphs with dynamic topology and joint weighting, improving skeleton-based action recognition over fixed-graph GCNs.

Findings

Achieves competitive results on Kinetics-Skeleton 400

Performs well on NTU RGB+D 60 and 120 datasets

Demonstrates the effectiveness of dynamic hypergraph modeling

Abstract

Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task. However, the skeleton graph cannot fully represent the motion information contained in skeleton data. In addition, the topology of the skeleton graph in the GCN-based methods is manually set according to natural connections, and it is fixed for all samples, which cannot well adapt to different situations. In this work, we propose a novel dynamic hypergraph convolutional networks (DHGCN) for skeleton-based action recognition. DHGCN uses hypergraph to represent the skeleton structure to effectively exploit the motion information contained in human joints. Each joint in the skeleton hypergraph is dynamically assigned the corresponding weight according to its moving, and the hypergraph topology in our model can be dynamically adjusted to different samples according to the relationship between the joints. Experimental results demonstrate that the performance of our model achieves competitive performance on three datasets: Kinetics-Skeleton 400, NTU RGB+D 60, and NTU RGB+D 120.