Research map / Video / Action recognition
GaitPart: Temporal Part-Based Model for Gait Recognition
Chao Fan, Yunjie Peng, Chunshui Cao, Xu Liu, Saihui Hou, Jiannan Chi, Yongzhen Huang, Qing Li, Zhiqiang He
Check 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 GaitPart instead of GaitSet | Gait recognition · CASIA-B NM#5-6 | rank-1 accuracy: 95.0 -> 96.2 | Improved |
| Use GaitPart instead of GaitSet | Gait recognition · CASIA-B BG#1-2 | rank-1 accuracy: 87.2 -> 91.5 | Improved |
| Use GaitPart instead of GaitSet | Gait recognition · CASIA-B CL#1-2 | rank-1 accuracy: 70.4 -> 78.7 | Improved |
| Use GaitPart instead of GaitSet | Gait recognition · OU-MVLP | mean rank-1 accuracy: 87.1 -> 88.7 | Improved |
| Add Focal Convolution in deeper blocks (ablation) | GaitPart · CASIA-B BG | rank-1 accuracy: 88.4 -> 91.5 | Improved |
| Add Focal Convolution in deeper blocks (ablation) | GaitPart · CASIA-B CL | rank-1 accuracy: 76.1 -> 78.7 | Improved |
| Add Focal Convolution to block 1 (ablation) | GaitPart · CASIA-B NM | rank-1 accuracy: 96.2 -> 95.8 | Hurt |
| Use both MTB scales (window sizes 3 and 5) (ablation) | GaitPart MCM · CASIA-B BG | rank-1 accuracy: 90.8 -> 91.5 | Improved |
| Add channel-wise attention to MTB (ablation) | GaitPart MCM · CASIA-B CL | rank-1 accuracy: 73.1 -> 78.7 | Improved |
| Use max rather than mean temporal pooling (ablation) | GaitPart MCM · CASIA-B CL | rank-1 accuracy: 70.1 -> 78.7 | Improved |
| Preserve temporal order instead of shuffling frames (ablation) | GaitPart · CASIA-B CL | rank-1 accuracy: 71.5 -> 78.7 | Improved |
Later papers that compared with this method
3 later accepted papers report GaitPart as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation (ICCV 2021 · better on 4 of 4 shared results)
- 3D Local Convolutional Neural Networks for Gait Recognition (ICCV 2021 · better on 4 of 4 shared results)
- Context-Sensitive Temporal Feature Learning for Gait Recognition (ICCV 2021 · better on 1 of 1 shared result)
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
- Learning Gait Representation From Massive Unlabelled Walking Videos: A Benchmark (TPAMI 2023 · similarity 0.90)
- Learning Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.89)
- Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · similarity 0.88)
- RA-GAR: A Richly Annotated Benchmark for Gait Attribute Recognition (AAAI 2025 · similarity 0.87)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.87)
- Vocabulary-Guided Gait Recognition (NeurIPS 2025 · 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.
