Domain adaptation for head pose estimation using relative pose consistency

HIGHLIGHTS

• who: IEEE TRANSACTIONS ON BIOMETRICS and collaborators from the (UNIVERSITY) have published the research: Domain Adaptation for Head Pose Estimation Using Relative Pose Consistency, in the Journal: (JOURNAL)
• what: The authors propose a semi-supervised learning strategy for head estimation based regularization. regularization enforces consistent network predictions under random image augmentations including pose-preserving and pose-altering augmentations. The authors propose a strategy to exploit the introduced by pose-altering augmentations between augmented image pairs to allow the network to benefit from labels during training unlabeled data. The authors evaluate the approach in a domain . . .
  

   

  

  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.