Given an image, we propose a hierarchical generative
model that classifies the overall scene, recognizes and segments
each object component, as well as annotates the image
with ...
In this paper, we address the problem of shadow detection and removal from single images of natural scenes. Different from traditional methods that explore pixel or edge informati...
Spectral clustering and eigenvector-based methods have become increasingly popular in segmentation and recognition. Although the choice of the pairwise similarity metric (or affin...
Sparse coding--that is, modelling data vectors as sparse linear combinations of basis elements--is widely used in machine learning, neuroscience, signal processing, and statistics...
Julien Mairal, Francis Bach, Jean Ponce, Guillermo...
Abstract. Obtaining high quality patient-specific flow velocity information is not an easy task. Available clinical data are usually poorly resolved and contain a significant amoun...