Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

TL;DR

This paper introduces a two-stream adaptive graph convolutional network that learns graph topology dynamically and models both first- and second-order skeleton information, significantly improving action recognition accuracy.

Contribution

The proposed 2s-AGCN adaptively learns graph topology end-to-end and incorporates second-order bone information, advancing skeleton-based action recognition methods.

Findings

Outperforms state-of-the-art on NTU-RGBD and Kinetics-Skeleton datasets.

Adaptive graph learning improves model flexibility and accuracy.

Two-stream framework effectively captures diverse skeleton features.

Abstract

In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance. However, in existing GCN-based methods, the topology of the graph is set manually, and it is fixed over all layers and input samples. This may not be optimal for the hierarchical GCN and diverse samples in action recognition tasks. In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods. In this work, we propose a novel two-stream adaptive graph convolutional network (2s-AGCN) for skeleton-based action recognition. The topology of the graph in our model can be either uniformly or individually learned by the BP algorithm in an end-to-end manner. This data-driven method increases the flexibility of the model for graph construction and brings more generality to adapt to various data samples. Moreover, a two-stream framework is proposed to model both the first-order and the second-order information simultaneously, which shows notable improvement for the recognition accuracy. Extensive experiments on the two large-scale datasets, NTU-RGBD and Kinetics-Skeleton, demonstrate that the performance of our model exceeds the state-of-the-art with a significant margin.