shlizee/Predict-Cluster
Repository for PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
This project helps classify human actions from body movement data without needing pre-labeled examples. You provide sequences of body keypoints (like joint positions over time), and it automatically groups similar movements together, identifying distinct actions. This is useful for researchers in human movement analysis, robotics, or surveillance who need to categorize activities from motion capture or video-derived skeleton data.
110 stars. No commits in the last 6 months.
Use this if you have raw body keypoint data from various movements and want to automatically categorize them into distinct actions without manually labeling each one.
Not ideal if you already have perfectly labeled action data and only need to train a supervised classification model.
Stars
110
Forks
22
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/shlizee/Predict-Cluster"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
kenshohara/3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)