Many facial image analysis methods rely on learningbased techniques such as Adaboost or SVMs to project classifiers based on the selection of local image filters (e.g., Haar and...
—One of the major challenges in multi-view imaging is the definition of a representation that reveals the intrinsic geometry of the visual information. Sparse image representati...
The choice of the over-complete dictionary that sparsely represents data is of prime importance for sparse codingbased image super-resolution. Sparse coding is a typical unsupervi...
It is now well established that sparse signal models are well suited for restoration tasks and can be effectively learned from audio, image, and video data. Recent research has be...
Julien Mairal, Francis Bach, Jean Ponce, Guillermo...