Gait recognition is an emerging biological recognition technology that identifies and verifies individuals based on their walking patterns. However, many current methods are limited in their use of temporal information. In order to fully harness the potential of gait recognition, it is crucial to consider temporal features at various granularities and spans. Hence, in this paper, we propose a novel framework named GaitGS, which aggregates temporal features in the granularity dimension and span dimension simultaneously. Specifically, Multi-Granularity Feature Extractor (MGFE) is proposed to focus on capturing the micro-motion and macro-motion information at the frame level and unit level respectively. Moreover, we present Multi-Span Feature Learning (MSFL) module to generate global and local temporal representations. On three popular gait datasets, extensive experiments demonstrate the state-of-the-art performance of our method. Our method achieves the Rank-1 accuracies of 92.9% (+0.5%), 52.0% (+1.4%), and 97.5% (+0.8%) on CASIA-B, GREW, and OU-MVLP respectively. The source code will be released soon.

翻译：步态识别是一种新兴的生物识别技术，通过个体的行走模式对其进行身份识别与验证。然而，现有多数方法在利用时序信息方面存在局限性。为充分挖掘步态识别的潜力，必须考虑不同粒度与跨度下的时序特征。为此，本文提出一种名为GaitGS的新型框架，该框架同时从粒度维度和跨度维度聚合时序特征。具体而言，我们设计了多粒度特征提取器（Multi-Granularity Feature Extractor, MGFE），分别从帧级和单元级捕捉微运动与宏运动信息；此外，还提出多跨度特征学习（Multi-Span Feature Learning, MSFL）模块，用于生成全局与局部时序表征。在三个主流步态数据集上的大量实验表明，本方法取得了最优性能。在CASIA-B、GREW和OU-MVLP数据集上，本方法的Rank-1准确率分别达到92.9%（+0.5%）、52.0%（+1.4%）和97.5%（+0.8%）。源代码将于近期公开。