用小波变换捕捉步态动态，提升骨骼识别在外观变化下的性能。
Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition
- 引入小波特征流，从关节速度中提取多尺度时频特征。
- 在CASIA-B数据集上显著提升多个强基线模型性能，尤其在背包/穿外套场景下。
- 无需修改主干网络或额外标注，可直接插拔使用。
基于骨骼的步态识别器擅长建模空间结构，但常忽略对外观变化至关重要的显式运动动态。本文提出一种即插即用的小波特征流，为任意骨骼主干网络补充关节速度的时频动态信息。具体地，对每个关节的速度序列进行连续小波变换（CWT），生成多尺度谱图，再通过轻量级多尺度CNN学习判别性动态特征。该描述符与主干表示融合后用于分类，无需修改主干架构或额外监督。在CASIA-B数据集上，该方法在多个强基线模型（如GaitMixer、GaitFormer、GaitGraph）上均实现稳定提升，并在附加到GaitMixer时达到新的骨骼基状态。在携带背包（BG）和穿外套（CL）等协变量偏移场景下性能提升尤为显著，凸显了显式时频建模与标准时空编码器的互补性。
原文摘要 · Abstract (English)
Skeleton-based gait recognizers excel at modeling spatial configurations but often underuse explicit motion dynamics that are crucial under appearance changes. We introduce a plug-and-play Wavelet Feature Stream that augments any skeleton backbone with time-frequency dynamics of joint velocities. Concretely, per-joint velocity sequences are transformed by the continuous wavelet transform (CWT) into multi-scale scalograms, from which a lightweight multi-scale CNN learns discriminative dynamic cues. The resulting descriptor is fused with the backbone representation for classification, requiring no changes to the backbone architecture or additional supervision. Across CASIA-B, the proposed stream delivers consistent gains on strong skeleton backbones (e.g., GaitMixer, GaitFormer, GaitGraph) and establishes a new skeleton-based state of the art when attached to GaitMixer. The improvements are especially pronounced under covariate shifts such as carrying bags (BG) and wearing coats (CL), highlighting the complementarity of explicit time-frequency modeling and standard spatio-temporal encoders.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。