Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs

TL;DR

This paper presents a lightweight, accurate skeleton-based two-person interaction recognition model that effectively captures inter- and intra-body joint relationships while reducing computational complexity.

Contribution

The authors introduce a novel architecture with middle fusion, factorized convolution, and a network stream for relative distance, improving accuracy and efficiency over existing methods.

Findings

Achieved state-of-the-art accuracy on NTU RGB+D datasets.

Reduced model complexity with factorized convolution techniques.

Demonstrated superior performance compared to conventional methods.

Abstract

Skeleton-based two-person interaction recognition has been gaining increasing attention as advancements are made in pose estimation and graph convolutional networks. Although the accuracy has been gradually improving, the increasing computational complexity makes it more impractical for a real-world environment. There is still room for accuracy improvement as the conventional methods do not fully represent the relationship between inter-body joints. In this paper, we propose a lightweight model for accurately recognizing two-person interactions. In addition to the architecture, which incorporates middle fusion, we introduce a factorized convolution technique to reduce the weight parameters of the model. We also introduce a network stream that accounts for relative distance changes between inter-body joints to improve accuracy. Experiments using two large-scale datasets, NTU RGB+D 60 and 120, show that our method simultaneously achieved the highest accuracy and relatively low computational complexity compared with the conventional methods.