Research map / Image generation / Autoregressive and latent generation
Learning A Unified Template for Gait Recognition
Panjian Huang, Saihui Hou, Junzhou Huang, Yongzhen Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Origins (generative template learning) (ablation) | gait baseline · Gait3D | Rank-1: 73.6 -> 75.8 | Improved |
| add Transferring Unified Template (ablation) | Origins-M · Gait3D | Rank-1: 74.4 -> 75.8 | Improved |
| add Diffusing Timestep Templates (ablation) | Origins-M · Gait3D | Rank-1: 75.3 -> 75.8 | Improved |
| add Transferring Unified Template (ablation) | Origins-M · Gait3D | mAP: 67.1 -> 67.0 | No clear effect |
| raise multi-heads from 8 to 16 (ablation) | Origins-M · Gait3D | Rank-1: 74.6 -> 75.8 | Improved |
| raise multi-heads from 16 to 32 (ablation) | Origins-M · Gait3D | Rank-1: 75.8 -> 75.2 | Hurt |
| raise timestep templates from 16 to 32 (ablation) | Origins-M · Gait3D | Rank-1: 75.8 -> 73.7 | Hurt |
| raise timestep templates from 8 to 16 (ablation) | Origins-M · Gait3D | Rank-1: 75.3 -> 75.8 | Improved |
| vary timestep templates 8, 16, 32 (ablation) | Origins-M · CASIA-B | Mean Rank-1: 95.6 / 95.7 / 95.5 | No clear effect |
| add Origins (ablation) | gait baseline · CASIA-B | Mean Rank-1: 92.8 -> 95.7 | Improved |
| add Origins (ablation) | gait baseline · CASIA-B | CL Rank-1: 84.4 -> 90.3 | Improved |
| add Origins (ablation) | gait baseline · Gait3D | Rank-5: 86.9 -> 86.8 | No clear effect |
Closest papers by meaning
- Learning Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.86)
- Vocabulary-Guided Gait Recognition (NeurIPS 2025 · similarity 0.86)
- On Denoising Walking Videos for Gait Recognition (CVPR 2025 · similarity 0.85)
- Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · similarity 0.84)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.84)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
