search

matyasbohacek / spoter

Repository accompanying the "Sign Pose-based Transformer for Word-level Sign Language Recognition" paper
https://spoter.signlanguagerecognition.com
Apache License 2.0
80 stars 24 forks source link

Training on new data #10

Closed Hamzah-Luqman closed 1 year ago

Hamzah-Luqman commented 1 year ago

Do you have the code of extracting the pose information from a video file and outputting it in the same format used in your code?

matyasbohacek commented 1 year ago

Thanks for your interest in our work!

To obtain data using Vision API (which was used in our original work, WACV'22 paper) in the supported format, use the Pose Data Annotator app (Mac App Store, GitHub with Swift code).

We will be providing more options of pose estimator formats — including example code — soon. Please stay tuned.

If this does not resolve your inquiry, please feel free to re-open the thread.