Uason-Chen/CTR-GCN
[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition"
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.
Stars
351
Forks
72
Language
Python
License
—
Category
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.
Higher-rated alternatives
patrikhuber/eos
A lightweight 3D Morphable Face Model library in modern C++
PeterL1n/BackgroundMattingV2
Real-Time High-Resolution Background Matting
PeterL1n/RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Zielon/MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]
BGU-CS-VIL/DeepMCBM
"A Deep Moving-camera Background Model" [Erez, Shapira Weber, and Freifeld, ECCV 2022]