Research map / Vision-language and multimodal / Cross-modal learning
MMGait: Towards Multi-Modal Gait Recognition
Chenye Wang, Qingyuan Cai, Saihui Hou, Aoqi Li, Yongzhen Huang
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 |
|---|---|---|---|
| fuse depth with RGB silhouette | MultiGait++ two-stream · MMGait CL | Rank-1 accuracy (%): 61.0 -> 80.3 | Improved |
| fuse LiDAR projected depth with RGB silhouette | MultiGait++ two-stream · MMGait CL | Rank-1 accuracy (%): 61.0 -> 80.7 | Improved |
| fuse event stream with RGB silhouette | MultiGait++ two-stream · MMGait CL | Rank-1 accuracy (%): 61.0 -> 62.1 | Improved |
| fuse pose heatmaps with RGB silhouette | MultiGait++ two-stream · MMGait CL | Rank-1 accuracy (%): 61.0 -> 64.0 | Improved |
| add Radar point cloud to LiDAR point cloud | LidarGait++ dual stream · MMGait CL | Rank-1 accuracy (%): 76.6 -> 80.4 | Improved |
| add Radar point cloud to LiDAR point cloud | LidarGait++ dual stream · MMGait NM | Rank-1 accuracy (%): 97.0 -> 96.3 | Hurt |
| use unified OmniGait instead of dedicated single-modality models | OmniGait RGB silhouette · MMGait CL | Rank-1 accuracy (%): 61.0 -> 44.9 | Hurt |
| use unified OmniGait instead of dedicated cross-modal model | RGB to Depth retrieval · MMGait NM | Rank-1 accuracy (%): 77.5 -> 87.0 | Improved |
| fuse RGB image with RGB silhouette | OmniGait · MMGait CL | Rank-1 accuracy (%): 44.9 -> 64.7 | Improved |
| fuse LiDAR projected depth with RGB silhouette | OmniGait · MMGait CL | Rank-1 accuracy (%): 44.9 -> 51.9 | Improved |
| fuse depth with RGB silhouette | OmniGait · MMGait CL | Rank-1 accuracy (%): 44.9 -> 49.1 | Improved |
| change covariate from normal walking to clothing change | cross-modal retrieval average · MMGait pairwise cross-modal | Rank-1 accuracy (%): 55.5 -> 28.4 | Hurt |
Closest papers by meaning
- OpenGait: A Comprehensive Benchmark Study for Gait Recognition Toward Better Practicality (TPAMI 2025 · similarity 0.93)
- OpenGait: Revisiting Gait Recognition Towards Better Practicality (CVPR 2023 · similarity 0.91)
- Walking Further: Semantic-Aware Multimodal Gait Recognition Under Long-Range Conditions (AAAI 2026 · similarity 0.91)
- GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set (TPAMI 2021 · similarity 0.90)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.88)
- Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · 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.
