Pa-tran: learning to estimate 3d hand pose with partial annotation

HIGHLIGHTS

• who: Tianze Yu et al. from the Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V T , Canada have published the Article: PA-Tran: Learning to Estimate 3D Hand Pose with Partial Annotation, in the Journal: Sensors 2023, 23, 1555. of /2023/
• what: In contrast the authors propose a deep-learning framework that jointly estimates the keypoints status and 3D hand pose from a single RGB image with two dependent branches. Investigating the percentage ranging from 50-100% the authors show that training with is more efficient (e_g achieving the best . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.