Research map / Video / Video segmentation and tracking
Dynamic Aggregated Network for Gait Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DANet instead of LagrangeGait | gait recognition · CASIA-B CL | rank-1 accuracy (%): 85.1 -> 89.9 | Helped |
| Add LCMB instead of using C2D convolution (ablation) | DANet · CASIA-B CL | rank-1 accuracy (%): 84.3 -> 89.9 | Helped |
| Add LCMB instead of using C3D convolution (ablation) | DANet · CASIA-B CL | rank-1 accuracy (%): 87.7 -> 89.9 | Helped |
| Add GMPA instead of Max aggregation (ablation) | DANet with LCMB · CASIA-B CL | rank-1 accuracy (%): 86.9 -> 89.9 | Helped |
| Add GMPA instead of Mean aggregation (ablation) | DANet with LCMB · CASIA-B CL | rank-1 accuracy (%): 87.1 -> 89.9 | Helped |
| Add GMPA instead of GeM aggregation (ablation) | DANet with LCMB · CASIA-B CL | rank-1 accuracy (%): 85.3 -> 89.9 | Helped |
| Add GMPA instead of MCM aggregation (ablation) | DANet with LCMB · CASIA-B CL | rank-1 accuracy (%): 85.4 -> 89.9 | Helped |
| Set spatial parts Npart=16 rather than 64 (ablation) | DANet · CASIA-B mean | rank-1 accuracy (%): 94.6 -> 92.5 | Hurt |
| Set spatial parts Npart=32 rather than 64 (ablation) | DANet · CASIA-B mean | rank-1 accuracy (%): 94.6 -> 94.2 | Hurt |
| Set lower-order motion patterns Npatt=1 rather than 16 (ablation) | DANet · CASIA-B mean | rank-1 accuracy (%): 94.6 -> 93.4 | Hurt |
| Set lower-order motion patterns Npatt=8 rather than 16 (ablation) | DANet · CASIA-B mean | rank-1 accuracy (%): 94.6 -> 93.1 | Hurt |
| Set lower-order motion patterns Npatt=32 rather than 16 (ablation) | DANet · CASIA-B mean | rank-1 accuracy (%): 94.6 -> 93.6 | Hurt |
Closest papers by meaning
- Learning Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.90)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.86)
- Vocabulary-Guided Gait Recognition (NeurIPS 2025 · similarity 0.85)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.85)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.84)
- RA-GAR: A Richly Annotated Benchmark for Gait Attribute Recognition (AAAI 2025 · 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.