Local Spatiotemporal Convolutional Network for Robust Gait Recognition

TL;DR

This paper introduces a simple yet effective dual-branch neural network architecture, LSTCN, that enhances gait recognition by capturing local spatiotemporal features through innovative pooling and convolution strategies.

Contribution

It proposes a novel LSTCN architecture with GBSP and LSTC layers, enabling efficient extraction of local spatiotemporal gait features using standard 2D convolutions.

Findings

LSTCN achieves superior gait recognition accuracy on benchmark datasets.

The model effectively captures local motion patterns with reduced computational complexity.

Asymmetric kernels further improve feature representation across domains.

Abstract

Gait recognition, as a promising biometric technology, identifies individuals through their unique walking patterns and offers distinctive advantages including non-invasiveness, long-range applicability, and resistance to deliberate disguise. Despite these merits, capturing the intrinsic motion patterns concealed within consecutive video frames remains challenging due to the complexity of video data and the interference of external covariates such as viewpoint changes, clothing variations, and carrying conditions. Existing approaches predominantly rely on either static appearance features extracted from individual silhouette frames or employ complex sequential models (\eg, LSTM, 3D convolutions) that demand substantial computational resources and sophisticated training strategies. To address these limitations, we propose a Local Spatiotemporal Convolutional Network (LSTCN), a structurally simple yet highly effective dual-branch architecture that endows standard two-dimensional convolutional networks with the capacity to extract temporal information. Specifically, we introduce a Global Bidirectional Spatial Pooling (GBSP) mechanism that reduces the dimensionality of gait tensors by decomposing spatial features into horizontal and vertical strip-based local representations, enabling the temporal dimension to participate in standard 2D convolution operations. Building upon this, we design a Local Spatiotemporal Convolutional (LSTC) layer that jointly processes temporal and spatial dimensions, allowing the network to adaptively learn strip-based gait motion patterns. We further extend this formulation with asymmetric convolution kernels that independently attend to the temporal, spatial, and joint spatiotemporal domains, thereby enriching the extracted feature representations.