uyoung-jeong/PoseBH
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation
This project offers an advanced way to accurately identify key points on bodies, whether human or animal, across various images or video frames. It takes in visual data and outputs precise coordinates for body landmarks, even when dealing with diverse datasets or limited labeled examples. Researchers and engineers working on computer vision applications will find this useful for robust pose estimation.
No commits in the last 6 months.
Use this if you need to precisely track body movements or identify specific anatomical points on humans or animals from images, especially when your training data comes from multiple sources or has incomplete labeling.
Not ideal if you are looking for a plug-and-play solution without any technical expertise in deep learning frameworks.
Stars
22
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/uyoung-jeong/PoseBH"
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)