Spatial Transformer Network on Skeleton-based Gait Recognition

TL;DR

This paper introduces Gait-TR, a robust skeleton-based gait recognition model combining spatial transformer and temporal convolutional networks, achieving state-of-the-art accuracy and robustness, especially in challenging scenarios like walking with coats.

Contribution

The paper proposes Gait-TR, a novel gait recognition model that outperforms existing skeleton-based methods in accuracy and robustness using spatial transformer frameworks.

Findings

Gait-TR achieves 90% Rank-1 accuracy in walking with coats cases.

Gait-TR outperforms silhouette-based models in robustness.

Spatial transformer extracts gait features more effectively than graph convolutional networks.

Abstract

Skeleton-based gait recognition models usually suffer from the robustness problem, as the Rank-1 accuracy varies from 90\% in normal walking cases to 70\% in walking with coats cases. In this work, we propose a state-of-the-art robust skeleton-based gait recognition model called Gait-TR, which is based on the combination of spatial transformer frameworks and temporal convolutional networks. Gait-TR achieves substantial improvements over other skeleton-based gait models with higher accuracy and better robustness on the well-known gait dataset CASIA-B. Particularly in walking with coats cases, Gait-TR get a 90\% Rank-1 gait recognition accuracy rate, which is higher than the best result of silhouette-based models, which usually have higher accuracy than the silhouette-based gait recognition models. Moreover, our experiment on CASIA-B shows that the spatial transformer can extract gait features from the human skeleton better than the widely used graph convolutional network.