Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

TL;DR

This paper introduces a multi-scale spatial-temporal graph convolutional network that effectively captures long-range dependencies in skeleton-based action recognition, significantly improving performance on benchmark datasets.

Contribution

It proposes novel multi-scale spatial and temporal graph convolution modules that enlarge receptive fields without extra parameters, enhancing the modeling of long-range dependencies.

Findings

Achieves state-of-the-art results on NTU RGB+D, NTU-120 RGB+D, and Kinetics-Skeleton datasets.

Enlarges receptive fields for better long-range dependency modeling.

Improves action recognition accuracy significantly.

Abstract

Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.