Purely bottom-up, unsupervised segmentation of a single
image into two segments remains a challenging task for
computer vision. The co-segmentation problem is the process
of joi...
The traditional SPM approach based on bag-of-features (BoF) must use nonlinear classifiers to achieve good image classification performance. This paper presents a simple but effec...
Most existing video denoising algorithms assume a single statistical model of image noise, e.g. additive Gaussian white noise, which often is violated in practice. In this paper, ...
This paper presents an algorithm for recovering the globally optimal 2D human figure detection using a loopy graph model. This is computationally challenging because the time comp...
Deciding whether a modal formula is satisfiable with respect to a given set of (global) assumptions is a question of fundamental importance in applications of logic in computer sc...