Abstract. Most CBIR systems use low-level visual features for representation and retrieval of images. Generally such methods suffer from the problems of high-dimensionality leadin...
Despite much research on patch-based descriptors, SIFT remains the gold standard for finding correspondences across images and recent descriptors focus primarily on improving spe...
We introduce an algorithm for a non-negative 3D tensor factorization for the purpose of establishing a local parts feature decomposition from an object class of images. In the pas...
People often recognize 3D objects by their boundary shape. Designing an algorithm for such a task is interesting and useful for retrieving objects from a shape database. In this pa...
Invariant representations in object recognition systems are generally obtained by pooling feature vectors over spatially local neighborhoods. But pooling is not local in the featu...
Y-Lan Boureau, Nicolas Le Roux, francis bach, Jean...