This paper addresses the problem of computing the trajectory of a camera from sparse positional measurements that have been obtained from visual localisation, and dense differenti...
This paper is concerned with computing graph edit distance. One of the criticisms that can be leveled at existing methods for computing graph edit distance is that it lacks the fo...
The Catchment Feature Model (CFM) addresses two questions in multimodal interaction: how do we bridge video and audio processing with the realities of human multimodal communicati...
Many of the computer vision algorithms have been posed in various forms of differential equations, derived from minimization of specific energy functionals, and the finite eleme...
We present a novel non-parametric unsupervised segmentation algorithm based on Region Competition [21]; but implemented within a Level Sets framework [11]. The key novelty of the ...
Conventional tracking approaches assume proximity in space, time and appearance of objects in successive observations. However, observations of objects are often widely separated ...
Building on recent progress in modeling filter response statistics of natural images we integrate a statistical model into a variational framework for image segmentation. Incorpo...
Detecting the dominant normal directions to the decision surface is an established technique for feature selection in high dimensional classification problems. Several approaches...
This paper presents a novel solution to the illuminant estimation problem: the problem of how, given an image of a scene taken under an unknown illuminant, we can recover an estim...
Graham D. Finlayson, Steven D. Hordley, Ingeborg T...