https://github.com/mvig-sjtu/wshp
Code for CVPR'18 spotlight "Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer"
https://github.com/mvig-sjtu/wshp
cvpr2018 human human-computer-interaction human-parsing human-robot-interaction human-understanding segmentation spotlight
Last synced: 2 months ago
JSON representation
Code for CVPR'18 spotlight "Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer"
- Host: GitHub
- URL: https://github.com/mvig-sjtu/wshp
- Owner: MVIG-SJTU
- License: other
- Created: 2018-05-10T16:39:13.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2021-10-09T12:37:32.000Z (over 3 years ago)
- Last Synced: 2025-03-31T18:19:56.634Z (3 months ago)
- Topics: cvpr2018, human, human-computer-interaction, human-parsing, human-robot-interaction, human-understanding, segmentation, spotlight
- Language: Python
- Size: 4.12 MB
- Stars: 300
- Watchers: 19
- Forks: 53
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer
[[arXiv](https://arxiv.org/abs/1805.04310)]
Transferring human body part parsing labels to raw images by exploiting the anatomical similarity. Some transferred results:
These results are used as extra training samples for the parsing network and can improve the part segmentation results:
## Getting Started
#### Demo video
Check out our demo video [here](https://youtu.be/nDqnMpE6b8s).
#### Parsing Network
Checkout `parsing_network` for training\testing\demo code of our parsing network.
#### Data generation
Checkout `data_generation` for code of using keypoints similarity to transfer parsing knowledge and generate synthetic training labels.
## Feedback
If you get any problems during usage, please open an issue.
## Citation
If you use this code for your research, please cite our paper:
```
@article{fang2018wshp,
title={Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer},
author={Fang, Hao-Shu and Lu, Guansong and Fang, Xiaolin and Xie, Jianwen and Tai, Yu-Wing and Lu, Cewu},
journal={CVPR},
year={2018}
}
```