Welcome to WLASL Homepage

WLASL is the largest video dataset for Word-Level American Sign Language (ASL) recognition, which features 2,000 common different words in ASL. We hope WLASL will facilitate the research in sign language understanding and eventually benefit the communication between deaf and hearing communities.

Download

Please clone our repository for downloading. We suggest reading README before using the dataset.

We strive to ensure our users have an easy access to WLASL. If you encounter any issue in downloading, e.g. invalid links, please contact dongxu.li@anu.edu.au for assistance.

News

• NEW: Pre-trained I3D and Pose-TGCN models and training code all released!
• Mar.29,2020 Now you can download all the WLASL videos by pressing a single button. Please check out our repo.
• Mar.16,2020 release of WLASL_v0.3.
• Mar. 11, 2020: release of WLASL_v0.2. Updated expired links.
• Mar. 5, 2020: Our work on WLASL dataset received WACV 2020 Best Paper Honourable Mention (Applications), out of nearly 1,000 submissions!
• Jan. 20, 2020: release of WLASL_v0.1! Pretrained models will follow shortly (or upon request for urgent use).

License

Licensed under the Computational Use of Data Agreement (C-UDA). Plaese refer to C-UDA-1.0.pdf for more information.

Disclaimer

All the WLASL data is intended for academic and computational use only. No commercial usage is allowed. We highly respect copyright and privacy. If you find WLASL violates your rights, please contact us.

Citation

Please cite the WLASL paper if it helps your research:

    @inproceedings{li2020word,
      title={Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison},
      author={Li, Dongxu and Rodriguez, Cristian and Yu, Xin and Li, Hongdong},
      booktitle={The IEEE Winter Conference on Applications of Computer Vision},
      pages={1459--1469},
      year={2020}
    }

and our CVPR 2020 Best Paper Finalist paper

@inproceedings{li2020transferring,
  title={Transferring cross-domain knowledge for video sign language recognition},
  author={Li, Dongxu and Yu, Xin and Xu, Chenchen and Petersson, Lars and Li, Hongdong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={6205--6214},
  year={2020}
}

Other works using WLASL dataset you might also be interested:

@inproceedings{li2020tspnet,
	title        = {TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation},
	author       = {Li, Dongxu and Xu, Chenchen and Yu, Xin and Zhang, Kaihao and Swift, Benjamin and Suominen, Hanna and Li, Hongdong},
	year         = 2020,
	booktitle    = {Advances in Neural Information Processing Systems},
	volume       = 33
}

Contacts

• Dongxu Li: dongxu.li@anu.edu.au
• Hongdong Li: hongdong.li@anu.edu.au