kenziyuliu/MS-G3D

[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"

50
/ 100
Established

This project helps classify human actions from skeleton data, identifying movements like standing up, clapping, or pointing. It takes in structured skeleton data, which represents the pose and movement of a person over time, and outputs a classification of the action being performed. This is primarily useful for researchers and developers working in computer vision, human-computer interaction, or surveillance who need to accurately recognize specific human activities.

455 stars. No commits in the last 6 months.

Use this if you need to precisely recognize a wide range of human actions from 3D skeleton data for applications like activity monitoring, sports analysis, or gesture recognition.

Not ideal if you are working with raw video footage or images and do not have access to pre-extracted skeleton data, or if your primary need is general object detection rather than human action recognition.

human-action-recognition skeleton-data-analysis human-computer-interaction video-surveillance sports-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

455

Forks

101

Language

Python

License

MIT

Last pushed

Aug 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kenziyuliu/MS-G3D"

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