Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single...
Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated object...
We propose a novel linear method for scale invariant figure ground separation in images and videos. Figure ground separation is treated as a superpixel labeling problem. We optim...
Conventional mutual information (MI)-based registration using pixel intensities is time-consuming and ignores spatial information, which can lead to misalignment. We propose a met...
Accurate and precise estimation of the noise variance is often of key importance as an input parameter for posterior image processing tasks. In MR images, background data is well s...