Learning the Face Prior for Bayesian Face Recognition




Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Aug 21, 2014

For the traditional Bayesian face recognition methods, a simple prior on face representation cannot cover large variations in facial poses, illuminations, expressions, aging, and occlusions in the wild. In this paper, we propose a new approach to learn the face prior for Bayesian face recognition. First, we extend Manifold Relevance Determination to learn the identity subspace for each individual automatically. Based on the structure of the learned identity subspaces, we then propose to estimate Gaussian mixture densities in the observation space with Gaussian process regression. During the training of our approach, the leave-set-out algorithm is also developed for overfitting avoidance. On extensive
experimental evaluations, the learned face prior can improve the performance of the traditional Bayesian face and other related methods significantly. It is also proved that the simple Bayesian face method with the learned face prior can handle the complex intra-personal variations such as large poses and large occlusions. Experiments on the challenging LFW benchmark shows that our algorithm outperforms most of the state-of-art methods.

  • Category

  • Song

  • Artist

    • YIRUMA
  • Album

    • 情書
  • Licensed to YouTube by

    • Wind Music TV (on behalf of 風潮音樂); Wixen Music Publishing, UBEM, UMPG Publishing, Sony ATV Publishing, Abramus Digital, ASCAP, PEDL, SOLAR Music Rights Management, CMRRA, União Brasileira de Compositores, and 18 Music Rights Societies


When autoplay is enabled, a suggested video will automatically play next.

Up next

to add this to Watch Later

Add to

Loading playlists...