LukasHedegaard/continual-skeletons
Official codebase for "Online Skeleton-based Action Recognition with Continual Spatio-Temporal Graph Convolutional Networks"
This project helps researchers and engineers working with human movement data to recognize actions more efficiently. It takes in skeleton data, which represents a person's body posture over time, and outputs an identified action. This is particularly useful for those who need to process real-time or streaming video data to understand human activities, like in surveillance or sports analysis.
No commits in the last 6 months.
Use this if you need to identify human actions from skeleton data in a continuous, step-by-step fashion with significantly reduced computational resources compared to traditional methods.
Not ideal if your primary need is static image analysis or if you are working with video data that isn't pre-processed into skeleton format.
Stars
29
Forks
10
Language
Python
License
—
Category
Last pushed
Apr 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LukasHedegaard/continual-skeletons"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pypose/pypose
A library for differentiable robotics on manifolds.
MarcoForte/FBA_Matting
Official repository for the paper F, B, Alpha Matting
snap-research/articulated-animation
Code for Motion Representations for Articulated Animation paper
foamliu/Deep-Image-Matting
Deep Image Matting
dyelax/Adversarial_Video_Generation
A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by...