Given a set of 3D model features and their 2D image, model based object recognition determines the correspondences between those features and hence computes the pose of the object...
Abstract. Diffusion tensor imaging (DT-MRI) is very sensitive to corrupting noise due to the non linear relationship between the diffusionweighted image intensities (DW-MRI) and th...
Abstract. Most of the approaches dedicated to fiber tracking from diffusionweighted MR data rely on a tensor model. However, the tensor model can only resolve a single fiber orient...
Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...
In recent years there has been a flurry of works on learning probabilistic belief networks. Current state of the art methods have been shown to be successful for two learning scen...