https://github.com/akira-l/SEEG

Code for SEEG: Semantic Energized Co-speech Gesture Generation
https://github.com/akira-l/SEEG

Last synced: about 2 months ago
JSON representation

Code for SEEG: Semantic Energized Co-speech Gesture Generation

• Host: GitHub
• URL: https://github.com/akira-l/SEEG
• Owner: akira-l
• License: other
• Created: 2022-03-07T07:44:27.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-12-03T11:14:13.000Z (almost 2 years ago)
• Last Synced: 2024-04-05T09:34:44.598Z (6 months ago)
• Language: Python
• Size: 451 KB
• Stars: 29
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

• awesome-conditional-content-generation - [Code

README

        
# SEEG 

This project is a pytorch implementation of *SEEG: Semantic Energized Co-speech Gesture Generation*. 

# Insight 

* Only learning beat gestures already performs comparably with the SOTA methods. 

* Introducing additional semantic-aware supervision can influence the gestures expressions. 

## Environment & Training 

This repository is developed and tested on Ubuntu 18.04, Python 3.6+, and PyTorch 1.3+. The environment is the same to [Trimodal Context](https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context).

This project is mainly developed based on [Trimodal Context](https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context). You can run this project by ``` bash train.sh ``` or the same commands in [Trimodal Context](https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context). 

## Citation

Please cite our CVPR2022 paper if you find our SEEG is helpful in your work:

```

@inproceedings{liang2022seeg,

  title={SEEG: Semantic Energized Co-speech Gesture Generation},

  author={Liang, Yuanzhi and Feng, Qianyu and Zhu, Linchao and Hu, Li and Pan, Pan and Yang, Yi}, 

  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

  year={2022}

}

```