Awesome

SignGraph: A Sign Sequence is Worth Graphs of Nodes

An implementation of the paper: SignGraph: A Sign Sequence is Worth Graphs of Nodes. (CVPR 2024) [paper]

Prerequisites

• This project is implemented in Pytorch (>1.8). Thus please install Pytorch first.

• ctcdecode==0.4 [parlance/ctcdecode]，for beam search decode.

• For these who failed install ctcdecode (and it always does), you can download ctcdecode here, unzip it, and try
  cd ctcdecode and pip install .

• Pealse follow this link to install pytorch geometric

• You can install other required modules by conducting pip install -r requirements.txt

Data Preparation

1. PHOENIX2014 dataset: Download the RWTH-PHOENIX-Weather 2014 Dataset [download link].

2. PHOENIX2014-T datasetDownload the RWTH-PHOENIX-Weather 2014 Dataset [download link]

3. CSL dataset： Request the CSL Dataset from this website [download link]

Download datasets and extract them, no further data preprocessing needed.

Weights

We make some imporvments of our code, and provide newest checkpoionts and better performance.

​To evaluate the pretrained model, choose the dataset from phoenix2014/phoenix2014-T/CSL/CSL-Daily in line 3 in ./config/baseline.yaml first, and run the command below：
python main.py --device your_device --load-weights path_to_weight.pt --phase test

Training

The priorities of configuration files are: command line > config file > default values of argparse. To train the SLR model, run the command below:

python main.py --device your_device

Note that you can choose the target dataset from phoenix2014/phoenix2014-T/CSL/CSL-Daily in line 3 in ./config/baseline.yaml.

Thanks

This repo is based on VAC (ICCV 2021), VIT (NIPS 2022) and RTG-Net (ACM MM2023)！

Citation

If you find this repo useful in your research works, please consider citing:

@inproceedings{gan2024signgraph,
  title={SignGraph: A Sign Sequence is Worth Graphs of Nodes},
  author={Gan, Shiwei and Yin, Yafeng and Jiang, Zhiwei and Wen, Hongkai and Xie, Lei and Lu, Sanglu},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={13470--13479},
  year={2024}
}

@inproceedings{gan2023towards,
  title={Towards Real-Time Sign Language Recognition and Translation on Edge Devices},
  author={Gan, Shiwei and Yin, Yafeng and Jiang, Zhiwei and Xie, Lei and Lu, Sanglu},
  booktitle={Proceedings of the 31st ACM International Conference on Multimedia},
  pages={4502--4512},
  year={2023}
}

@inproceedings{gan2023contrastive,
  title={Contrastive learning for sign language recognition and translation},
  author={Gan, Shiwei and Yin, Yafeng and Jiang, Zhiwei and Xia, Kang and Xie, Lei and Lu, Sanglu},
  booktitle={Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23},
  pages={763--772},
  year={2023}
}

@article{han2022vision,
  title={Vision gnn: An image is worth graph of nodes},
  author={Han, Kai and Wang, Yunhe and Guo, Jianyuan and Tang, Yehui and Wu, Enhua},
  journal={Advances in neural information processing systems},
  volume={35},
  pages={8291--8303},
  year={2022}
}