Segmentation of video objects from background is a popular computer vision problem and has many important applications. Most existing methods are either computationally expensive ...
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
We propose an energy-based framework for approximating surfaces from a cloud of point measurements corrupted by noise and outliers. Our energy assigns a tangent plane to each (noi...
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...
The problem of multi-target tracking is comprised of two distinct, but tightly coupled challenges: (i) the naturally discrete problem of data association, i.e. assigning image obs...