Research map / Video / Action recognition
Gait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition
Saihui Hou, Chunshui Cao, Xu Liu, 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 lateral connections (without Compact Block) over GaitSet-L (ablation) | GLN · CASIA-B CL | rank-1 accuracy (%): 75.27 -> 77.22 | Improved |
| add lateral connections (without Compact Block) over GaitSet-L (ablation) | GLN · CASIA-B BG | rank-1 accuracy (%): 91.52 -> 91.98 | Improved |
| add Compact Block (23808-d to 256-d) (ablation) | GLN · CASIA-B NM | rank-1 accuracy (%): 95.58 -> 96.88 | Improved |
| add Compact Block (23808-d to 256-d) (ablation) | GLN · CASIA-B BG | rank-1 accuracy (%): 91.98 -> 94.04 | Improved |
| add Compact Block (23808-d to 256-d) (ablation) | GLN · CASIA-B CL | rank-1 accuracy (%): 77.22 -> 77.50 | No clear effect |
| add label smooth (ablation) | GLN · CASIA-B NM | rank-1 accuracy (%): 96.48 -> 96.88 | Improved |
| add label smooth (ablation) | GLN · CASIA-B CL | rank-1 accuracy (%): 77.03 -> 77.50 | Improved |
| add Lateral Pretraining before Global Training (ablation) | GLN · CASIA-B BG | rank-1 accuracy (%): 93.07 -> 94.04 | Improved |
| add Dropout and ReLU to Compact Block (BN+FC+BN to full) (ablation) | GLN · CASIA-B CL | rank-1 accuracy (%): 70.05 -> 77.50 | Improved |
| add Dropout to Compact Block (BN+ReLU+FC+BN to full) (ablation) | GLN · CASIA-B CL | rank-1 accuracy (%): 71.48 -> 77.50 | Improved |
| add ReLU to Compact Block (BN+Dropout+FC+BN to full) (ablation) | GLN · CASIA-B CL | rank-1 accuracy (%): 75.23 -> 77.50 | Improved |
| change output dimension from 128/512 to 256 (ablation) | GLN · CASIA-B CL | rank-1 accuracy (%): 76.84 (128), 77.10 (512), 77.50 (256) | Mixed |
Closest papers by meaning
- GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set (TPAMI 2021 · similarity 0.89)
- Deep Gait Recognition: A Survey (TPAMI 2022 · similarity 0.89)
- Learning Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.89)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.87)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.86)
- Vocabulary-Guided Gait Recognition (NeurIPS 2025 · similarity 0.85)
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.
