Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition

• URL: http://arxiv.org/abs/2604.03002v1
• Date: Fri, 03 Apr 2026 12:32:44 GMT
• Title: Explicit Time-Frequency Dynamics for Skeleton-Based Gait Recognition
• Abstract summary: Skeleton-based gait recognizers excel at modeling but often underuse explicit motion dynamics that are crucial under appearance changes.<n>We introduce a plug-and-play Feature Stream that augments any skeleton with time-frequency dynamics of joint velocities.<n>Across CASIA-B, the proposed stream delivers consistent gains on strong skeleton backbones.
• Score: 2.354172698385588
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Single-Stream Multi-Feature Fusion with Temporal Robustness for Gait Emotion Recognition [2.055138638073669]
  3D skeleton-based gait emotion recognition faces high annotation costs, data scarcity, and poor generalization on heterogeneous data.<n>This paper proposes SV-GCN, a single-stream multi-feature fusion framework with temporal invariance.
  arXiv  Detail & Related papers  (2026-09-10T15:11:51Z)
• GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis [94.20462261657525]
  GrainGS is a dynamic framework that combines a hierarchical anchor scaffold with per-Gaussian deformation.<n>It achieves high reconstruction quality, real-time novel view synthesis, and compact storage.
  arXiv  Detail & Related papers  (2026-07-23T15:52:35Z)
• SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition [54.97159515886273]
  SkelHCC is a unified skeleton hyperbolic CLIP-driven cache adaptation framework for one-shot action recognition.<n>By leveraging the negative curvature and exponential volume growth of hyperbolic geometry, EH-HCLIP naturally encodes the joint-part-body hierarchy of human anatomy.
  arXiv  Detail & Related papers  (2026-06-02T13:13:27Z)
• Gait Recognition with Temporal Kolmogorov-Arnold Networks [24.11167872887211]
  Gait recognition is a biometric modality that identifies individuals from their characteristic walking patterns.<n>To address these challenges, we introduce a Temporal Kolmogorov-Arnold Network (TKAN) for gait recognition.<n>The proposed model replaces fixed edge weights with learnable one-dimensional functions and incorporates a two-level memory mechanism.
  arXiv  Detail & Related papers  (2026-04-11T02:28:26Z)
• KGS-GCN: Enhancing Sparse Skeleton Sensing via Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Action Recognition [20.09080176203823]
  KGS-GCN is a graph convolutional network that integrates kinematics-driven Gaussian splatting with probabilistic topology.<n>Our framework offers a robust solution for processing lowfidelity sensor data.
  arXiv  Detail & Related papers  (2026-03-16T07:47:33Z)
• Towards Arbitrary Motion Completing via Hierarchical Continuous Representation [64.6525112550758]
  We propose a novel parametric activation-induced hierarchical implicit representation framework, called NAME, based on Implicit Representations (INRs)<n>Our method introduces a hierarchical temporal encoding mechanism that extracts features from motion sequences at multiple temporal scales, enabling effective capture of intricate temporal patterns.
  arXiv  Detail & Related papers  (2025-12-24T14:07:04Z)
• TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition [59.99922360648663]
  TSkel-Mamba is a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics.<n>The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition.
  arXiv  Detail & Related papers  (2025-12-12T11:55:16Z)
• Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer [18.459822172890473]
  We introduce a frequency-aware attention module to unweave skeleton frequency representations. We also develop a mixed transformer architecture to incorporate spatial features with frequency features. Experiments show that FreqMiXFormer outperforms SOTA on 3 popular skeleton recognition datasets.
  arXiv  Detail & Related papers  (2024-07-17T05:47:27Z)
• Multi-Scale Spatial-Temporal Self-Attention Graph Convolutional Networks for Skeleton-based Action Recognition [0.0]
  In this paper, we propose self-attention GCN hybrid model, Multi-Scale Spatial-Temporal self-attention (MSST)-GCN. We utilize spatial self-attention module with adaptive topology to understand intra-frame interactions within a frame among different body parts, and temporal self-attention module to examine correlations between frames of a node.
  arXiv  Detail & Related papers  (2024-04-03T10:25:45Z)
• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching [77.6989219290789]
  One-shot skeleton action recognition aims to learn a skeleton action recognition model with a single training sample. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching.
  arXiv  Detail & Related papers  (2023-07-14T11:52:10Z)
• DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition [77.87404524458809]
  We propose a new framework for skeleton-based action recognition, namely Dynamic Group Spatio-Temporal GCN (DG-STGCN) It consists of two modules, DG-GCN and DG-TCN, respectively, for spatial and temporal modeling. DG-STGCN consistently outperforms state-of-the-art methods, often by a notable margin.
  arXiv  Detail & Related papers  (2022-10-12T03:17:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.