Error Concealment by Means of Motion Refinement and Regularized Bregman Divergence.
Alessandra Martins CoelhoVania Vieira EstrelaFelipe P. do CarmoSandro R. FernandesPublished in: IDEAL (2012)
Keyphrases
- error concealment
- bregman divergences
- motion vectors
- motion estimation
- visual quality
- maximum entropy
- packet loss
- cost sensitive
- motion field
- information theoretic
- image sequences
- nearest neighbor
- bitstream
- temporal error concealment
- mahalanobis distance
- video quality
- motion model
- reference frame
- optical flow
- moving objects
- loss function
- learning theory
- exponential family
- video sequences
- negative matrix factorization
- kl divergence
- theoretical guarantees
- video data
- macroblock
- least squares
- active learning
- computational complexity