We propose a face difference model that decomposes face difference into three components, intrinsic difference, transformation difference, and noise. Using the face difference mod...
This paper introduces the Located Hidden Random Field (LHRF), a conditional model for simultaneous part-based detection and segmentation of objects of a given class. Given a traini...
We present an algorithm which uses information from both surface reflectance and illumination variation to solve for colour constancy. Most colour constancy algorithms assume that ...
This paper presents a method for camera pose tracking that uses a partial knowledge about the scene. The method is based on monocular vision Simultaneous Localization And Mapping ...
We address the problem of 3D model based vehicle localization in calibrated traffic scenes. A wireframe vehicle model is set up as prior information and an efficient local gradien...