Abstract
Gait recognition aims to distinguish different walking patterns by analyzing video-level human silhouettes, rather than relying on appearance information. Previous research on gait recognition has primarily focused on extracting local or global spatial-temporal representations, while overlooking the intrinsic periodic features of gait sequences, which, when fully utilized, can significantly enhance performance. In this work, we propose a plug-and-play strategy, called Temporal Periodic Alignment (TPA), which leverages the periodic nature and fine-grained temporal dependencies of gait patterns. The TPA strategy comprises two key components. The first component is Adaptive Fourier-transform Position Encoding (AFPE), which adaptively converts features and discrete-time signals into embeddings that are sensitive to periodic walking patterns. The second component is the Temporal Aggregation Module (TAM), which separates embeddings into trend and seasonal components, and extracts meaningful temporal correlations to identify primary components, while filtering out random noise. We present a simple and effective baseline method for gait recognition, based on the TPA strategy. Extensive experiments conducted on three popular public datasets (CASIA-B, OU-MVLP, and GREW) demonstrate that our proposed method achieves state-of-the-art performance on multiple benchmark tests.
Abstract (translated)
步态识别旨在通过分析视频级别人类轮廓,而不是依赖外观信息,区分不同的步态模式。以往的步态识别研究主要关注提取局部或全球的空间和时间表示,而忽视了步态序列的内在周期性特征,这些特征如果得到充分利用,可以显著提高性能。在本文中,我们提出了一种插件式策略,称为时间周期性匹配(TPA),利用步态模式的周期性特性和精细的时间依赖关系。TPA策略由两个关键组件组成。第一个组件是自适应傅里叶位置编码(AFPE),它自适应地将特征和离散时间信号转换为嵌入,这些嵌入对周期性步态模式敏感。第二个组件是时间聚合模块(TAM),它将嵌入分离为趋势和季节性组件,并提取有意义的时间相关度,以识别主要组件,同时过滤掉随机噪声。我们提出了一种基于TPA策略的简单有效基准方法,在三个流行的公共数据集(CASIA-B、OU-MVLP和GREW)上进行了大量实验,证明了我们提出的方法在多个基准测试中实现了最先进的性能。
URL
https://arxiv.org/abs/2307.13259