In this paper, we propose a novel framework of object categorization, namely layered object categorization, which takes advantage of hierarchical category information and performs...
A natural requirement in pairwise image registration is that the resulting deformation is independent of the order of the images. This constraint is typically achieved via a symmet...
Mert R. Sabuncu, B. T. Thomas Yeo, Koen Van Leem...
We present a dynamic inference algorithm in a globally parameterized nonlinear manifold and demonstrate it on the problem of visual tracking. An appearance manifold is usually non...
In this paper, we propose a Bayesian approach to video object segmentation. Our method consists of two stages. In the first stage, we partition the video data into a set of 3D wate...
Many machine learning algorithms can be formulated as a generalized eigenvalue problem. One major limitation of such formulation is that the generalized eigenvalue problem is comp...