HyperGait：利用超图释放解析在野外步态识别中的力量
HyperGait: Unleashing the Power of Parsing for Gait Recognition in the Wild via Hypergraph
将人体解析序列作为步态识别输入，并用超图卷积分别建模身体部位间的高阶空间关系与部位时序动态，为野外步态识别提供可复用的高阶相关性建模思路。
原文依据 The SHCM extracts fine-grained relationships between human body parts through the hypergraph.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近年来，步态解析序列因其比二值轮廓和基于关键点的骨架具有更高的信息熵而日益流行。然而，现有的基于解析的步态识别方法尚未充分探索不同位置、语义和时序动态层次特征之间的复杂非线性关系，即高阶相关性。为释放人体部位间解析与时序动态的力量，本文提出了一种新颖的基于超图的步态识别框架，名为HyperGait。HyperGait包含一个全局检测头和两个精心设计的模块。具体而言，空间超图卷积模块（SHCM）和时序超图卷积模块（THCM）分别被设计用于探索高阶空间层次和时序层次的特征。SHCM通过超图提取人体部位间的细粒度关系。THCM在时序相关的人体部位间执行高阶时序信息处理。在两个大规模步态数据集Gait3D和SUSTech1K上的综合实验表明，所提出的HyperGait具有优越的性能。在极具挑战性的真实世界场景中，仅以解析作为输入，我们的HyperGait在Gait3D数据集上达到了80.5%的Rank-1准确率。
英文原文摘要 1349 字符
In recent years, the gait parsing sequence has become increasingly popular due to its higher information entropy than the binary silhouette and the keypoint-based skeleton. However, existing parsing-based gait recognition methods have not fully explored the complex, non-linear relationships between features at different positions, semantic, and temporal dynamics levels, i.e., higher-order correlations. To unleash the power of parsing between human body parts and temporal dynamics, this paper proposes a novel hypergraph-based gait recognition framework, named HyperGait. The HyperGait contains a global head and two elaborately-designed modules. In particular, the Spatial Hypergraph Convolutional Module (SHCM) and the Temporal Hypergraph Convolutional Module (THCM) are designed to explore the high-order spatial-level and temporal-level features, respectively.The SHCM extracts fine-grained relationships between human body parts through the hypergraph.The THCM performs the high-order temporal information between temporally related human body parts.Comprehensive experiments on two large-scale gait datasets, i.e., Gait3D and SUSTech1K, show the superior performance of our proposed HyperGait.In highly challenging real-world scenarios, with only parsing as input, our HyperGait achieves the Rank-1 accuracy of 80.5% on the Gait3D dataset.