Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.03002 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911564978716672 |
|---|---|
| author | Ko, Seoyeon Song, Yeojin Chung, Egene Quagliato, Luca Lee, Taeyong Noh, Junhyug |
| author_facet | Ko, Seoyeon Song, Yeojin Chung, Egene Quagliato, Luca Lee, Taeyong Noh, Junhyug |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03002 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition Ko, Seoyeon Song, Yeojin Chung, Egene Quagliato, Luca Lee, Taeyong Noh, Junhyug Computer Vision and Pattern Recognition 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. |
| title | Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.03002 |