Yonsei Korean Sign Language Dataset

The Yonsei Korean Sign Language Dataset consists of depth-only video data collected from 20 volunteers for 50 Korean Sign Language vocabularies.


  • Data Collection Environment: Apple iPhone X depth camera

  • Dataset Size: Approximately 10,000 videos

    • Approx. 5,000 raw depth-only videos

    • Approx. 5,000 refactored depth-only videos (Detailed refactoring scheme will soon be open)

  • Words included in Dataset: Refer to the README in the dataset archive

  • Number of Study Participants: 20 people

  • Licence: This dataset is licensed under a Creative Commons Attribution 4.0 International License.

  • Please cite this dataset in your work using the following publication, where the dataset was initially introduced.


[Bibtex format]
@article{park21sugo,author = {Park, HyeonJung and Lee, Youngki and Ko, JeongGil},title = {Enabling Real-time Sign Language Translation on Mobile Platforms with On-board Depth Cameras},year = {2021},issue_date = {June 2021},publisher = {Association for Computing Machinery},address = {New York, NY, USA},volume = {5},number = {2},journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.},month = jun,}
[Plain text format]
Hyeonjung Park, Youngki Lee, JeongGil Ko. "Enabling Real-time Sign Language Translation on Mobile Platforms with On-board Depth Cameras", Proceedings of the ACM (PACM) on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 5, Issue 2, June 2020.