Gait recognition, which aims at identifying individuals by their walking patterns, has recently drawn increasing research attention. However, gait recognition still suffers from the conflicts between the limited binary visual clues of the silhouette and numerous covariates with diverse scales, which brings challenges to the model's adaptiveness. In this paper, we address this conflict by developing a novel MetaGait that learns to learn an omni sample adaptive representation. Towards this goal, MetaGait injects meta-knowledge, which could guide the model to perceive sample-specific properties, into the calibration network of the attention mechanism to improve the adaptiveness from the omni-scale, omni-dimension, and omni-process perspectives. Specifically, we leverage the meta-knowledge across the entire process, where Meta Triple Attention and Meta Temporal Pooling are presented respectively to adaptively capture omni-scale dependency from spatial/channel/temporal dimensions simultaneously and to adaptively aggregate temporal information through integrating the merits of three complementary temporal aggregation methods. Extensive experiments demonstrate the state-of-the-art performance of the proposed MetaGait. On CASIA-B, we achieve rank-1 accuracy of 98.7%, 96.0%, and 89.3% under three conditions, respectively. On OU-MVLP, we achieve rank-1 accuracy of 92.4%.

翻译：步态识别旨在通过行走模式识别个体，近期受到越来越多的研究关注。然而，步态识别仍面临轮廓的有限二元视觉线索与具有多种尺度的众多协变量之间的矛盾，这对模型的自适应性提出了挑战。本文通过开发新型MetaGait来解决这一矛盾，该模型学习一种全方位样本自适应表征。为实现此目标，MetaGait将元知识注入注意力机制的校准网络，以引导模型感知样本特定属性，从而从全方位尺度、全方位维度和全方位过程角度提升自适应性。具体而言，我们利用整个过程中的元知识，分别提出元三重注意力和元时间池化，以从空间/通道/时间维度同时自适应捕获全方位尺度依赖关系，并通过整合三种互补时间聚合方法的优势自适应聚合时间信息。大量实验表明，所提出的MetaGait达到了最优性能。在CASIA-B数据集上，我们在三种条件下分别获得98.7%、96.0%和89.3%的rank-1准确率；在OU-MVLP数据集上，我们获得92.4%的rank-1准确率。