Abstract
Gait recognition has attracted increasing attention from academia and industry as a human recognition technology from a distance in non-intrusive ways without requiring cooperation. Although advanced methods have achieved impressive success in lab scenarios, most of them perform poorly in the wild. Recently, some Convolution Neural Networks (ConvNets) based methods have been proposed to address the issue of gait recognition in the wild. However, the temporal receptive field obtained by convolution operations is limited for long gait sequences. If directly replacing convolution blocks with visual transformer blocks, the model may not enhance a local temporal receptive field, which is important for covering a complete gait cycle. To address this issue, we design a Global-Local Temporal Receptive Field Network (GLGait). GLGait employs a Global-Local Temporal Module (GLTM) to establish a global-local temporal receptive field, which mainly consists of a Pseudo Global Temporal Self-Attention (PGTA) and a temporal convolution operation. Specifically, PGTA is used to obtain a pseudo global temporal receptive field with less memory and computation complexity compared with a multi-head self-attention (MHSA). The temporal convolution operation is used to enhance the local temporal receptive field. Besides, it can also aggregate pseudo global temporal receptive field to a true holistic temporal receptive field. Furthermore, we also propose a Center-Augmented Triplet Loss (CTL) in GLGait to reduce the intra-class distance and expand the positive samples in the training stage. Extensive experiments show that our method obtains state-of-the-art results on in-the-wild datasets, $i.e.$, Gait3D and GREW. The code is available at this https URL.
Abstract (translated)
基于距离的非侵入性的人脸识别技术引起了学术界和产业界越来越多的关注。尽管在实验室场景中,先进的方法取得了显著的成功,但大多数方法在野外表现不佳。最近,一些基于卷积神经网络(ConvNets)的方法被提出来解决野地中步态识别的问题。然而,卷积操作获得的时域接收域对于较长的步态序列是有限的。如果直接用视觉Transformer块替换卷积模块,模型可能不会增强局部时域接收域,这对于覆盖完整的步态周期的目的很重要。为了解决这个问题,我们设计了一个全局-局部时域接收域网络(GLGait)。GLGait采用一个全局-局部时域模块(GLTM)来建立全局-局部时域接收域,主要是由一个伪全局时域自注意(PGTA)和一个时域卷积操作组成。具体来说,PGTA用于获得比多头自注意(MHSA)更少记忆和计算复杂度的伪全局时域接收域。时域卷积操作用于增强局部时域接收域。此外,它还可以将伪全局时域接收域聚合到真正的全时域接收域中。此外,我们还提出了GLGait中的中心增强三元组损失(CTL),以减少类内距离并扩大训练阶段中的积极样本。大量实验证明,我们的方法在野外数据集(即Gait3D和GREW)上的表现达到了最先进的水平。代码可在此https://url.cn/中获取。
URL
https://arxiv.org/abs/2408.06834