We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
An automated method for left ventricle detection in MR cardiac images is presented. Ventricle detection is the rst step in a fully automated segmentation system used to compute vo...
Nicolae Duta, Anil K. Jain, Marie-Pierre Dubuisson...
Abstract. Sparse signal models learned from data are widely used in audio, image, and video restoration. They have recently been generalized to discriminative image understanding t...
Julien Mairal, Marius Leordeanu, Francis Bach, Mar...
While discriminative training (e.g., CRF, structural SVM) holds much promise for machine translation, image segmentation, and clustering, the complex inference these applications ...
Protein fold recognition is a key step towards inferring the tertiary structures from amino-acid sequences. Complex folds such as those consisting of interacting structural repeat...