Research map / Video / Video segmentation and tracking
Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition
ZhengXian Wu, Chuanrui Zhang, Shen'Ao Jiang, Hangrui Xu, Zirui Liao, Luyuan Zhang, Li Huaqiu, Peng Jiao, Haoqian Wang
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 text branch on top of MTCM (ablation) | LMGait · CCPG (Mean) | Rank-1 (%): 86.9 -> 88.5 | Improved |
| add MTCM without text branch (ablation) | LMGait baseline · CCPG (Mean) | Rank-1 (%): 87.2 -> 86.9 | Hurt |
| add 3D-CNN temporal module without text branch (ablation) | LMGait baseline · CCPG (Mean) | Rank-1 (%): 87.2 -> 86.4 | Hurt |
| add pixel-wise temporal extraction PTE (ablation) | MTCM · CCPG (Mean) | Rank-1 (%): 87.5 -> 88.5 | Improved |
| add RTE temporal difference (ablation) | MTCM · CCPG (Mean) | Rank-1 (%): 88.2 -> 88.5 | Improved |
| add RTE 3D convolution (ablation) | MTCM · CCPG (Mean) | Rank-1 (%): 87.9 -> 88.5 | Improved |
| add MAM refinement with correct text (ablation) | LMGait · CCPG (Mean) | Rank-1 (%): 87.6 -> 88.5 | Improved |
| add MAM refinement under misleading text (ablation) | LMGait · CCPG (Mean) | Rank-1 (%): 86.1 -> 87.1 | Improved |
| feed misleading text without MAM instead of no text (ablation) | LMGait · CCPG (Mean) | Rank-1 (%): 86.1 vs 88.5 | Hurt |
| use hand-designed gait text instead of MLLM-generated text (ablation) | LMGait · CCPG (Mean) | Rank-1 (%): 88.1 -> 88.5 | Improved |
| use DINOv2 instead of CLIP image encoder (ablation) | LMGait · CCPG (Mean) | Rank-1 (%): 73.9 -> 88.5 | Improved |
| LMGait vs BigGait (RGB input) | LMGait · CCPG (Mean) | Rank-1 (%): 87.2 -> 88.5 | Improved |
Closest papers by meaning
- Bridging Gait Recognition and Large Language Models Sequence Modeling (CVPR 2025 · similarity 0.92)
- Vocabulary-Guided Gait Recognition (NeurIPS 2025 · similarity 0.91)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.91)
- Unlocking Motion from Large Vision Models with a Semantic and Kinematic Duality for Gait Recognition (CVPR 2026 · similarity 0.91)
- Learning Visual Prompt for Gait Recognition (CVPR 2024 · similarity 0.89)
- BigGait: Learning Gait Representation You Want by Large Vision Models (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.
