GaitMM: Multi-Granularity Motion Sequence Learning for Gait Recognition

TL;DR

GaitMM introduces a multi-granularity motion representation network that effectively captures discriminative gait features by combining full-body and fine-grained sequences, achieving state-of-the-art results in gait recognition.

Contribution

The paper proposes a novel multi-granularity motion learning framework with a combined sequence module and a frame-wise compression strategy for improved gait recognition.

Findings

Achieves state-of-the-art performance on CASIA-B and OUMVLP datasets.

Effectively captures part-independent spatio-temporal gait features.

Outperforms existing methods in gait recognition accuracy.

Abstract

Gait recognition aims to identify individual-specific walking patterns by observing the different periodic movements of each body part. However, most existing methods treat each part equally and fail to account for the data redundancy caused by the different step frequencies and sampling rates of gait sequences. In this study, we propose a multi-granularity motion representation network (GaitMM) for gait sequence learning. In GaitMM, we design a combined full-body and fine-grained sequence learning module (FFSL) to explore part-independent spatio-temporal representations. Moreover, we utilize a frame-wise compression strategy, referred to as multi-scale motion aggregation (MSMA), to capture discriminative information in the gait sequence. Experiments on two public datasets, CASIA-B and OUMVLP, show that our approach reaches state-of-the-art performances.