Gait Recognition in the Wild with Multi-hop Temporal Switch

TL;DR

This paper introduces MTSGait, a novel multi-hop temporal switch network that models gait dynamics efficiently using 2D convolutions, improving accuracy in real-world gait recognition scenarios.

Contribution

The paper proposes a new gait recognition network with multi-scale temporal modeling using 2D convolutions and a novel sampling strategy for robustness in wild scenes.

Findings

Achieves superior accuracy on GREW and Gait3D datasets.

Reduces model complexity compared to 3D convolution methods.

Enhances robustness with non-cyclic continuous sampling.

Abstract

Existing studies for gait recognition are dominated by in-the-lab scenarios. Since people live in real-world senses, gait recognition in the wild is a more practical problem that has recently attracted the attention of the community of multimedia and computer vision. Current methods that obtain state-of-the-art performance on in-the-lab benchmarks achieve much worse accuracy on the recently proposed in-the-wild datasets because these methods can hardly model the varied temporal dynamics of gait sequences in unconstrained scenes. Therefore, this paper presents a novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes. Concretely, we design a novel gait recognition network, named Multi-hop Temporal Switch Network (MTSGait), to learn spatial features and multi-scale temporal features simultaneously. Different from existing methods that use 3D convolutions for temporal modeling, our MTSGait models the temporal dynamics of gait sequences by 2D convolutions. By this means, it achieves high efficiency with fewer model parameters and reduces the difficulty in optimization compared with 3D convolution-based models. Based on the specific design of the 2D convolution kernels, our method can eliminate the misalignment of features among adjacent frames. In addition, a new sampling strategy, i.e., non-cyclic continuous sampling, is proposed to make the model learn more robust temporal features. Finally, the proposed method achieves superior performance on two public gait in-the-wild datasets, i.e., GREW and Gait3D, compared with state-of-the-art methods.