Research map / Video / Action recognition
HyperGait: Unleashing the Power of Parsing for Gait Recognition in the Wild via Hypergraph
Jinkai Zheng, Jiaqing Wei, Xinxiang Jin, Yaoqi Sun, Xichun Sheng, Ming Li, Liangqiong Qu, Xinchen Liu, Wu Liu
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 spatial hypergraph convolution module (SHCM) (ablation) | Backbone + Global Head · Gait3D | Rank-1: 75.7 -> 76.7 | Improved |
| add temporal hypergraph convolution module (THCM) (ablation) | Backbone + Global Head · Gait3D | Rank-1: 75.7 -> 77.9 | Improved |
| add both SHCM and THCM (ablation) | Backbone + Global Head · Gait3D | Rank-1: 75.7 -> 80.5 | Improved |
| spatial hypergraph instead of spatial GCN (ablation) | Baseline · Gait3D | Rank-1: 76.2 -> 76.7 | Improved |
| temporal hypergraph instead of temporal GCN (ablation) | Baseline · Gait3D | Rank-1: 76.8 -> 77.9 | Improved |
| hypergraph modules instead of S-GCN + T-GCN combination (ablation) | Baseline · Gait3D | Rank-1: 78.1 -> 80.5 | Improved |
| add spatial GCN to baseline (ablation) | Backbone + Global Head · Gait3D | mINP: 49.8 -> 47.3 | Hurt |
| spatial hypergraph threshold 0.4 vs 0.6 (ablation) | HyperGait · Gait3D | Rank-1: 77.8 -> 80.5 | Improved |
| spatial hypergraph threshold 0.9 vs 0.4 (ablation) | HyperGait · Gait3D | Rank-1: 80.5 -> 78.8 | Hurt |
| 10 temporal segments instead of 5 (ablation) | HyperGait · Gait3D | Rank-1: 79.3 -> 80.5 | Improved |
| increase temporal kNN from 3 to 7 (ablation) | HyperGait · Gait3D | Rank-1: 80.5 -> 78.8 | Hurt |
| HyperGait on occlusion probe vs GaitHeat | HyperGait · SUSTech1K occlusion | Rank-1: 53.2 vs 61.4 | Hurt |
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.
- DyGait — DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition (ICCV 2023) · 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 Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.87)
- RA-GAR: A Richly Annotated Benchmark for Gait Attribute Recognition (AAAI 2025 · similarity 0.86)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.86)
- Vocabulary-Guided Gait Recognition (NeurIPS 2025 · similarity 0.86)
- SkeletonGait: Gait Recognition Using Skeleton Maps (AAAI 2024 · similarity 0.86)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.86)
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.
