A major problem in object recognition is that a novel image of a given object can be different from all previously seen images. Images can vary considerably due to changes in viewi...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
Abstract. A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences ...
This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled v...
We consider the problem of approximating the 3D scan of a real object through an affine combination of examples. Common approaches depend either on the explicit estimation of poi...