Hierarchical Spatio-Temporal Representation Learning for Gait Recognition

TL;DR

This paper introduces a hierarchical spatio-temporal learning framework for gait recognition that captures multi-level body motion features, improving accuracy in identifying individuals based on walking styles in unconstrained environments.

Contribution

The paper proposes a novel hierarchical approach combining multi-level body structure analysis with adaptive motion extraction and pooling for enhanced gait recognition.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Balances model accuracy with computational complexity.

Effectively captures multi-scale gait features.

Abstract

Gait recognition is a biometric technique that identifies individuals by their unique walking styles, which is suitable for unconstrained environments and has a wide range of applications. While current methods focus on exploiting body part-based representations, they often neglect the hierarchical dependencies between local motion patterns. In this paper, we propose a hierarchical spatio-temporal representation learning (HSTL) framework for extracting gait features from coarse to fine. Our framework starts with a hierarchical clustering analysis to recover multi-level body structures from the whole body to local details. Next, an adaptive region-based motion extractor (ARME) is designed to learn region-independent motion features. The proposed HSTL then stacks multiple ARMEs in a top-down manner, with each ARME corresponding to a specific partition level of the hierarchy. An adaptive spatio-temporal pooling (ASTP) module is used to capture gait features at different levels of detail to perform hierarchical feature mapping. Finally, a frame-level temporal aggregation (FTA) module is employed to reduce redundant information in gait sequences through multi-scale temporal downsampling. Extensive experiments on CASIA-B, OUMVLP, GREW, and Gait3D datasets demonstrate that our method outperforms the state-of-the-art while maintaining a reasonable balance between model accuracy and complexity.