Research map / Video / Video segmentation and tracking
Hierarchical Motion Understanding via Motion Programs
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Supply target poses generated by motion programs to SepConv | SepConv video interpolation · PoseWarp 8x | average keypoint difference: 3.275 -> 2.840 | Helped |
| Supply target poses generated by motion programs to SepConv | SepConv video interpolation · GolfDB 8x | average keypoint difference: 6.900 -> 5.669 | Helped |
| Supply target poses generated by motion programs to SepConv | SepConv video interpolation · GolfDB 2x | average keypoint difference: 2.308 -> 2.432 | Hurt |
| Add input pose heatmaps without motion-program target poses (ablation) | SepConv video interpolation · GolfDB 8x | average keypoint difference: 6.900 -> 7.317 | Hurt |
| Encode poses as motion programs | GolfDB train-set pose representation · GolfDB train set | parameters per video: 1,623 -> 253 | Helped |
| Use abstract programs with loops to detect repetitive segments | Motion programs · cardio00 | precision: 88.57 | Helped |
| Use abstract programs with loops to detect repetitive segments | Motion programs · cardio00 | recall: 58.06 | Hurt |
| Use abstract programs with loops to detect repetitive segments | Motion programs · cardio01 | recall: 90.47 | Helped |
Closest papers by meaning
- HuMoCon: Concept Discovery for Human Motion Understanding (CVPR 2025 · similarity 0.88)
- HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding (NeurIPS 2026 · similarity 0.87)
- Scaling Large Motion Models with Million-Level Human Motions (ICML 2025 · similarity 0.87)
- Towards Understanding Camera Motions in Any Video (NeurIPS 2025 · similarity 0.86)
- ProMotion: Prototypes As Motion Learners (CVPR 2024 · similarity 0.86)
- HumMUSS: Human Motion Understanding using State Space Models (CVPR 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.