Improving Skeleton-based Action Recognition with Interactive Object Information

TL;DR

This paper enhances skeleton-based action recognition by integrating interactive object information through a novel graph convolutional network, datasets, and augmentation techniques, achieving state-of-the-art accuracy.

Contribution

It introduces object nodes into skeleton graphs, proposes ST-VGCN for variable graph modeling, and develops data augmentation and fusion modules to improve recognition performance.

Findings

Achieved 96.7% accuracy on NTU RGB+D 60 cross-subject split.

Created new datasets JXGC 24 and NTU RGB+D+Object 60 with over 2 million object nodes.

Surpassed previous state-of-the-art results on multiple benchmarks.

Abstract

Human skeleton information is important in skeleton-based action recognition, which provides a simple and efficient way to describe human pose. However, existing skeleton-based methods focus more on the skeleton, ignoring the objects interacting with humans, resulting in poor performance in recognizing actions that involve object interactions. We propose a new action recognition framework introducing object nodes to supplement absent interactive object information. We also propose Spatial Temporal Variable Graph Convolutional Networks (ST-VGCN) to effectively model the Variable Graph (VG) containing object nodes. Specifically, in order to validate the role of interactive object information, by leveraging a simple self-training approach, we establish a new dataset, JXGC 24, and an extended dataset, NTU RGB+D+Object 60, including more than 2 million additional object nodes. At the same time, we designe the Variable Graph construction method to accommodate a variable number of nodes for graph structure. Additionally, we are the first to explore the overfitting issue introduced by incorporating additional object information, and we propose a VG-based data augmentation method to address this issue, called Random Node Attack. Finally, regarding the network structure, we introduce two fusion modules, CAF and WNPool, along with a novel Node Balance Loss, to enhance the comprehensive performance by effectively fusing and balancing skeleton and object node information. Our method surpasses the previous state-of-the-art on multiple skeleton-based action recognition benchmarks. The accuracy of our method on NTU RGB+D 60 cross-subject split is 96.7\%, and on cross-view split, it is 99.2\%.