Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition
This work addresses gait recognition for biometric identification under covariate shifts, representing an incremental improvement by enhancing existing methods with complementary dynamics modeling.
The paper tackled the problem of skeleton-based gait recognition under appearance changes by introducing a plug-and-play Wavelet Feature Stream that adds explicit time-frequency dynamics of joint velocities to existing backbones, achieving new state-of-the-art results on CASIA-B with significant gains in challenging conditions like carrying bags and wearing coats.
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.