Signal-SGN：一种通过学习时频动力学进行骨骼动作识别的脉冲图卷积网络
Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics
AI总结：
针对GCN能耗高、SNN难以建模骨骼动力学的问题，提出融合时频特征的脉冲图卷积网络Signal-SGN，在三个数据集上实现优于现有SNN方法的性能与能效，接近GCN效果且大幅降低能耗。
摘要：
在基于多模态骨骼的动作识别任务中，图卷积网络（GCNs）是有效的模型，但其依赖浮点计算的特性导致能耗较高，限制了其在电池供电设备中的应用。脉冲神经网络（SNNs）虽然能效高，但难以对骨骼动力学建模，效果不够理想。我们提出Signal-SGN（脉冲图卷积网络），将骨骼序列的时间维度作为脉冲时间步，将特征表示为多维离散随机信号以进行时频域特征提取。该模型结合一维脉冲图卷积（1D-SGC）模块和频率脉冲卷积（FSC）模块，从脉冲形式表示的骨骼数据中提取特征。此外，还提出多尺度小波变换特征融合（MWTF）模块，用于提取动态脉冲特征并捕捉特定频率特征，提升分类性能。在三个大规模数据集上的实验表明，Signal-SGN的准确率和计算效率均优于现有最先进的基于SNN的方法，性能与GCN方法相当，且理论能耗显著降低。
英文摘要：
For multimodal skeleton-based action recognition, Graph Convolutional Networks (GCNs) are effective models. Still, their reliance on floating-point computations leads to high energy consumption, limiting their applicability in battery-powered devices. While energy-efficient, Spiking Neural Networks (SNNs) struggle to model skeleton dynamics, leading to suboptimal solutions. We propose Signal-SGN (Spiking Graph Convolutional Network), which utilizes the temporal dimension of skeleton sequences as the spike time steps and represents features as multi-dimensional discrete stochastic signals for temporal-frequency domain feature extraction. It combines the 1D Spiking Graph Convolution (1D-SGC) module and the Frequency Spiking Convolution (FSC) module to extract features from the skeleton represented as spiking form. Additionally, the Multi-Scale Wavelet Transform Feature Fusion (MWTF) module is proposed to extract dynamic spiking features and capture frequency-specific characteristics, enhancing classification performance. Experiments across three large-scale datasets reveal Signal-SGN exceeding state-of-the-art SNN-based methods in accuracy and computational efficiency while attaining comparable performance with GCN methods and significantly reducing theoretical energy consumption.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
