Graphical models are a framework for representing and exploiting prior conditional independence structures within distributions using graphs. In the Gaussian case, these models are...
Abstract—We present the estimation and evaluation of deployment models for sensor networks that exploit different amounts of a priori information. Topologies generated from the m...
Abstract--This paper presents a new wavelet-based image denoising method, which extends a recently emerged "geometrical" Bayesian framework. The new method combines three...
Aleksandra Pizurica, Wilfried Philips, Ignace Lema...
Given several related learning tasks, we propose a nonparametric Bayesian model that captures task relatedness by assuming that the task parameters (i.e., predictors) share a late...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...