Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/foruck/kinematic-phrases
https://github.com/foruck/kinematic-phrases
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/foruck/kinematic-phrases
- Owner: Foruck
- License: mit
- Created: 2024-08-14T09:19:11.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-08-16T07:53:48.000Z (5 months ago)
- Last Synced: 2024-08-16T09:00:52.571Z (5 months ago)
- Size: 659 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases (ECCV 2024)
## KP Extraction
1. Download SMPL(X) models and put them in ``models``.
2. Run ``python kp.py`` to extract KP sequence corresponding to the sample motion sequence.## TODOs
- [x] Kinematic Pharases list in `KP`.
- [x] Kinematic Prompt Generation (KPG) prompts in `kpg.txt`.
- [x] A data sample is available in `sample`.
- [x] Code for KP extraction.
- [ ] Code for KPG benchmarking.
- [ ] Code for Kinematic Phrases Base aggregation.