Research map / 3D vision / Human pose estimation
ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users
Xiangyu Yin, Boyuan Yang, Weichen Liu, Qiyao Xue, Abrar Alamri, Goeran Fiedler, Wei Gao
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 |
|---|---|---|---|
| fine-tune on ProGait | YOLO11 · ProGait VOS | mIoU: 0.784 -> 0.847 | Improved |
| fine-tune on ProGait | YOLO11 · ProGait VOS (inside bars) | mIoU: 0.831 -> 0.815 | Hurt |
| fine-tune on ProGait | RTMPose · ProGait 2D HPE | AP: 0.855 -> 0.947 | Improved |
| fine-tune on ProGait | RTMPose · ProGait 2D HPE lower-body | AP-leg: 0.804 -> 0.918 | Improved |
| change Grounded SAM2 text prompt from 'a person' to 'a human with prosthetic leg' | Grounded SAM2 · ProGait VOS | mIoU: 0.358 -> 0.964 | Improved |
| change Grounded SAM2 prompt from 'a person' to 'an amputee' | Grounded SAM2 · ProGait VOS | mIoU: 0.358 -> 0.905 | Improved |
| use sagittal view alone instead of the whole dataset (both views) (ablation) | LSTM-ProGait · ProGait gait classification | top-1 accuracy: 0.372 -> 0.826 | Improved |
| use frontal view alone instead of sagittal view (ablation) | LSTM-ProGait · ProGait gait classification | top-1 accuracy: 0.826 -> 0.510 | Hurt |
| use lower-body keypoints only instead of all 23 keypoints (ablation) | LSTM-ProGait · ProGait gait classification (whole dataset) | top-1 accuracy: 0.372 -> 0.384 | No clear effect |
| use lower-body keypoints only (sagittal) (ablation) | LSTM-ProGait · ProGait gait classification (sagittal) | top-1 accuracy: 0.826 -> 0.773 | Hurt |
| fine-tune classification head on ProGait | GaitGraph2 · ProGait gait classification | top-1 accuracy: 0.200 -> 0.440 | Improved |
| fine-tune classification head on ProGait | GPGait · ProGait gait classification | top-1 accuracy: 0.388 -> 0.457 | Improved |
Closest papers by meaning
- SkeletonGait: Gait Recognition Using Skeleton Maps (AAAI 2024 · similarity 0.85)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.84)
- BigGait: Learning Gait Representation You Want by Large Vision Models (CVPR 2024 · similarity 0.84)
- ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion Forecasting (NeurIPS 2024 · similarity 0.83)
- VidSole: A Multimodal Dataset for Joint Kinetics Quantification and Disease Detection with Deep Learning (AAAI 2025 · similarity 0.83)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.82)
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.
