Geometric deformable models based on the level set method have become very popular in the last several years. To overcome an inherent limitation in accuracy while maintaining comp...
In the context of shape and image modeling by manifold learning, we focus on the problem of denoising. A set of shapes or images being known through given samples, we capture its s...
Abstract. We present a technique for learning the parameters of a continuousstate Markov random field (MRF) model of optical flow, by minimizing the training loss for a set of grou...
A Multi-target user interface is composed of a series of interconnected variations of the same user interfaces, but tailored for different targets or different contexts of use. Wh...
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...