Given an image, we propose a hierarchical generative
model that classifies the overall scene, recognizes and segments
each object component, as well as annotates the image
with ...
This paper presents a model of cloth dyeing using the characteristics of the thread and weave pattern. The proposed dyeing model is based on Fick's second law that defines th...
Optical flow estimation is one of the main subjects in computer vision. Many methods developed to compute the motion fields are built using standard heuristic formulation. In this...
In this paper, we present a patch-based variational Bayesian framework of image processing using the language of factor graphs (FGs). The variable and factor nodes of FGs represen...
Image classification is a well-studied and hard problem in computer vision. We extend a proven solution for classifying web spam to handle images. We exploit the link structure of...