Research map / Label-efficient and robust learning / Recognition and long-tail
Gait Recognition in the Wild: A Benchmark
Zheng Zhu, Xianda Guo, Tian Yang, Junjie Huang, Jiankang Deng, Guan Huang, Dalong Du, Jiwen Lu, Jie Zhou
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 |
|---|---|---|---|
| increase training identities from 1K to 20K (ablation) | GaitSet · GREW test | Rank-1 accuracy (%): 28.0% -> 46.28% | Improved |
| increase training identities from 1K to 20K (ablation) | TS-CNN · GREW test | Rank-1 accuracy (%): 9.50% -> 13.55% | Improved |
| increase training identities from 1K to 20K (ablation) | GEINet · GREW test | Rank-1 accuracy (%): 5.32 -> 6.82 | No clear effect |
| increase training identities from 1K to 20K (ablation) | GaitPart · GREW test | Rank-1 accuracy (%): 26.39 -> 44.01 | Improved |
| increase training identities from 1K to 20K (ablation) | PoseGait and GaitGraph · GREW test | Rank-1 accuracy (%): 0.13 -> 0.23 (PoseGait), 0.25 -> 1.31 (GaitGraph) | No clear effect |
| double test identities from 1K to 2K (ablation) | GaitSet · GREW test | Rank-1 accuracy (%): 57.45% -> 49.83% | Hurt |
| add 233K distractor sequences to the gallery (ablation) | GaitSet · GREW test | Rank-1 accuracy (%): 46.28% -> 41.97% | Hurt |
| pre-train on GREW then fine-tune on CASIA-B (ablation) | GaitSet · CASIA-B | Rank-1 accuracy (%): 83.64% -> 84.48% | Improved |
| train on GREW and test directly on CASIA-B without fine-tuning (ablation) | GaitSet · CASIA-B | Rank-1 accuracy (%): 83.64% -> 45.14% | Hurt |
| use carrying (backpack) versus no carrying | GaitSet · GREW test | Rank-1 accuracy (%): 52.36 -> 48.83 | Hurt |
| probe with lift-stuff versus no carrying | GaitSet · GREW test | Rank-1 accuracy (%): 52.36 -> 45.66 | Hurt |
| probe with skirt versus all dressing | GaitSet · GREW test | Rank-1 accuracy (%): 46.28 -> 44.30 | Hurt |
Closest papers by meaning
- Gait Recognition in the Wild: A Large-Scale Benchmark and NAS-Based Baseline (TPAMI 2025 · similarity 0.98)
- Learning Gait Representation From Massive Unlabelled Walking Videos: A Benchmark (TPAMI 2023 · similarity 0.93)
- RA-GAR: A Richly Annotated Benchmark for Gait Attribute Recognition (AAAI 2025 · similarity 0.90)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.90)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.88)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.88)
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.
