Uason-Chen/CTR-GCN

[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition"

49
/ 100
Emerging

This project helps researchers and computer vision scientists accurately identify human actions from skeleton movement data. It takes in raw or pre-processed skeletal joint coordinates from video recordings and outputs classified actions, such as 'walking' or 'waving'. This is ideal for those working on pose estimation, surveillance, human-computer interaction, or sports analysis.

351 stars. No commits in the last 6 months.

Use this if you need to train or evaluate models that recognize diverse human actions from skeletal motion data with high accuracy.

Not ideal if you are working with raw video frames or images directly and do not have access to pre-extracted skeleton data.

action-recognition human-pose-analysis computer-vision-research motion-capture-analysis behavioral-analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

351

Forks

72

Language

Python

License

Last pushed

Nov 20, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Uason-Chen/CTR-GCN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.