Research map / Vision-language and multimodal / Cross-modal learning
Gait-X: Exploring X modality for Generalized Gait Recognition
Zengbin Wang, Saihui Hou, Junjie Li, Xu Liu, Chunshui Cao, Yongzhen Huang, Siye Wang, Man Zhang
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 single X modality (mask, DC removal, AC suppression) (ablation) | Baseline GaitBase · CCPG gait protocol | mean rank-1: 76.7 -> 84.5 | Improved |
| add decomposition training (ablation) | Baseline · CCPG gait protocol | mean rank-1: 76.7 -> 84.9 | Improved |
| combine X modality and decomposition training (ablation) | Gait-X · CCPG gait protocol | mean rank-1: 84.9 -> 87.3 | Improved |
| X modality plus decomposition training cross-domain (ablation) | Gait-X · CCPG to CASIA-B | mean rank-1: 38.4 -> 64.9 | Improved |
| add mask (background removal) (ablation) | Gait-X · CCPG to CASIA-B | mean rank-1: 54.0 -> 64.9 | Improved |
| add mask (background removal) (ablation) | Gait-X · CCPG gait protocol | mean rank-1: 86.1 -> 87.3 | Improved |
| add DC removal and AC suppression to single X modality (ablation) | single X modality · CCPG gait protocol | mean rank-1: 79.7 -> 84.5 | Improved |
| use 30 frames instead of 8 frames (ablation) | Gait-X · CCPG gait protocol | mean rank-1: 87.3 -> 88.6 | Improved |
| use 30 frames instead of 8 frames (ablation) | Gait-X · CCPG to CASIA-B | mean rank-1: 64.9 -> 62.4 | Hurt |
| Gait-X versus BigGait | Gait-X · CCPG to SUSTech1K | overall rank-1: 56.4 -> 73.4 | Improved |
| Gait-X versus BigGait on night subset | Gait-X · CCPG to SUSTech1K | night rank-1: 44.8 -> 43.4 | Hurt |
| Gait-X versus BigGait | Gait-X · SUSTech1K night (within-domain) | rank-1: 85.3 -> 71.9 | Hurt |
Closest papers by meaning
- Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · similarity 0.88)
- QAGait: Revisit Gait Recognition from a Quality Perspective (AAAI 2024 · similarity 0.87)
- Vocabulary-Guided Gait Recognition (NeurIPS 2025 · similarity 0.87)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.86)
- On Denoising Walking Videos for Gait Recognition (CVPR 2025 · similarity 0.86)
- SkeletonGait: Gait Recognition Using Skeleton Maps (AAAI 2024 · similarity 0.86)
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.
