A novel filter feature selection technique is introduced. The method exploits the information conveyed by the evolution of the training samples weights similarly to the Adaboost a...
State-of-the-art person re-identication methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with a single ve...
We propose a discrete regularization framework on weighted graphs of arbitrary topology, which leads to a family of nonlinear filters, such as the bilateral filter or the TV digi...
We present an nD image processing paradigm to obtain high precision estimates of geometric object properties such as volume, surface area, and length from digitized data. We prove...
We describe a model-based object tracking system that updates the configuration parameters of an object model based upon information gathered from a sequence of monocular images. ...