Gait Recognition with Temporal Kolmogorov-Arnold Networks

TL;DR

This paper introduces a novel Temporal Kolmogorov-Arnold Network (TKAN) for gait recognition, enhancing robustness and efficiency in modeling both local gait cycles and long-term motion trends.

Contribution

The paper proposes a new TKAN model that replaces fixed weights with learnable functions and uses a two-level memory mechanism for improved gait recognition.

Findings

Achieves strong recognition performance on CASIA-B dataset.

Effectively models both cycle-level dynamics and long-term motion.

Maintains a compact backbone with efficient temporal modeling.

Abstract

Gait recognition is a biometric modality that identifies individuals from their characteristic walking patterns. Unlike conventional biometric traits, gait can be acquired at a distance and without active subject cooperation, making it suitable for surveillance and public safety applications. Nevertheless, silhouette-based temporal models remain sensitive to long sequences, observation noise, and appearance-related covariates. Recurrent architectures often struggle to preserve information from earlier frames and are inherently sequential to optimize, whereas transformer-based models typically require greater computational resources and larger training sets and may be sensitive to irregular sequence lengths and noisy inputs. These limitations reduce robustness under clothing variation, carrying conditions, and view changes, while also hindering the joint modeling of local gait cycles and longer-term motion trends. To address these challenges, we introduce a Temporal Kolmogorov-Arnold Network (TKAN) for gait recognition. The proposed model replaces fixed edge weights with learnable one-dimensional functions and incorporates a two-level memory mechanism consisting of short-term RKAN sublayers and a gated long-term pathway. This design enables efficient modeling of both cycle-level dynamics and broader temporal context while maintaining a compact backbone. Experiments on the CASIA-B dataset indicate that the proposed CNN+TKAN framework achieves strong recognition performance under the reported evaluation setting.