Skip to content

jingyunx/Deformation-Flow-Based-Two-stream-Network-for-Lip-Reading

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deformation-Flow-Based-Two-stream-Network

Introduction

This is the implementation of the proposed method in "Deformation Flow Based Two-Stream Network for Lip Reading". Our paper can be found here.

Dependencies

  • Python 3.5+
  • PyTorch 1.0+
  • Others

Dataset

This model is trained on LRW (grayscale) and LRW-1000 (RGB).

Training And Testing

You can train or test the model as follows:

python train.py options.toml

or

python test.py options.toml

To load the pretrained model, please download the model here, unzip it and copy all the 6 files to "./weights/".

Reference

If this work is useful for your research, please cite our work:

  title={Deformation Flow Based Two-Stream Network for Lip Reading},
  author={Xiao, Jingyun and Yang, Shuang and Zhang, Yuanhang and Shan, Shiguang and Chen, Xilin},
  booktitle={2020 15th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2020)},
  year={2020},
  organization={IEEE}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages