Research map / 3D vision / Human pose estimation
GPGait: Generalized Pose-based Gait Recognition
Yang Fu, Shibei Meng, Saihui Hou, Xuecai Hu, 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 |
|---|---|---|---|
| use Human-Oriented Transformation instead of spine-unit normalization (ablation) | GPGait · Gait3D -> CASIA-B | Rank-1 accuracy: 15.74 -> 36.17 | Improved |
| use HOT instead of dataset-independent normalization (ablation) | GPGait · CASIA-B -> Gait3D | Rank-1 accuracy: 1.50 -> 8.90 | Improved |
| use dataset-independent normalization instead of HOT on source domain (ablation) | GPGait · CASIA-B (source) | Rank-1 accuracy: 81.01 -> 87.03 | Mixed |
| apply HOT to GaitTR on CASIA-B (ablation) | GaitTR · CASIA-B (source) | Rank-1 accuracy: 90.22 -> 64.37 | Hurt |
| apply HOT to GaitTR on Gait3D -> CASIA-B (ablation) | GaitTR · Gait3D -> CASIA-B | Rank-1 accuracy: 4.12 -> 21.74 | Improved |
| combine joint, bone and angle descriptors (ablation) | GPGait · Gait3D -> CASIA-B | Rank-1 accuracy: 31.12 -> 36.17 | Improved |
| use multi-branch instead of single-branch network (ablation) | GPGait · Gait3D -> CASIA-B | Rank-1 accuracy: 33.04 -> 36.17 | Improved |
| add body-part partition masks to PAGCN (ablation) | GPGait · CASIA-B -> Gait3D | Rank-1 accuracy: 7.10 -> 8.90 | Improved |
| add part partition masks to PAGCN (ablation) | GPGait · Gait3D -> CASIA-B | Rank-1 accuracy: 35.15 -> 36.17 | Improved |
| GPGait versus pose-based baselines on source domain | OUMVLP-Pose source · OUMVLP-Pose | Rank-1 accuracy: 70.68 -> 59.11 | Hurt |
Closest papers by meaning
- From FastPoseGait to GPGait++: Bridging the Past and Future for Pose-Based Gait Recognition (TPAMI 2025 · similarity 0.96)
- Cut out the Middleman: Revisiting Pose-based Gait Recognition (ECCV 2024 · similarity 0.93)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.89)
- Learning Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.88)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.87)
- SkeletonGait: Gait Recognition Using Skeleton Maps (AAAI 2024 · similarity 0.87)
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.
