Research map / Label-efficient and robust learning / Recognition and long-tail
Gait Recognition in the Wild: A Large-Scale Benchmark and NAS-Based Baseline
Xianda Guo, Zheng Dong Zhu, Tian Yang, Beibei Lin, Junjie Huang, Jiankang Deng, Guan Huang, Jie Zhou, Jiwen Lu
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 cross-entropy loss instead of triplet loss alone (ablation) | SPOSGait · GREW test | Rank-1: 62.54 -> 74.41 | Improved |
| use 0.1*triplet + 1.0*cross-entropy instead of cross-entropy alone (ablation) | SPOSGait · GREW test | Rank-1: 74.41 -> 74.80 | Improved |
| raise triplet weight to 1.0 with cross-entropy 1.0 (ablation) | SPOSGait · GREW test | Rank-1: 74.80 -> 72.75 | Hurt |
| add skip connections (ablation) | SPOSGait · GREW test | Rank-1: 53.37 -> 70.05 | Improved |
| add BatchNorm (ablation) | SPOSGait · GREW test | Rank-1 | Improved |
| add horizontal flip augmentation (ablation) | SPOSGait · GREW test | Rank-1: 70.05 -> 73.69 | Improved |
| add rotation augmentation (ablation) | SPOSGait · GREW test | Rank-1: 70.05 -> 73.02 | Improved |
| add perspective transformation augmentation (ablation) | SPOSGait · GREW test | Rank-1: 70.05 -> 73.27 | Improved |
| add affine transformation augmentation (ablation) | SPOSGait · GREW test | Rank-1: 70.05 -> 66.59 | Hurt |
| add random erasing augmentation (ablation) | SPOSGait · GREW test | Rank-1: 70.05 -> 70.58 | Improved |
| combine horizontal flip and rotation (ablation) | SPOSGait · GREW test | Rank-1: 73.69 -> 74.80 | Improved |
| add perspective transformation to flip and rotation (ablation) | SPOSGait · GREW test | Rank-1: 74.80 -> 74.97 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GaitSet — GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition (AAAI 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Gait Recognition in the Wild: A Benchmark (ICCV 2021 · similarity 0.98)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.91)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.90)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.90)
- RA-GAR: A Richly Annotated Benchmark for Gait Attribute Recognition (AAAI 2025 · similarity 0.89)
- Learning Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.89)
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.
