Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
Recognizing object classes and their 3D viewpoints is an
important problem in computer vision. Based on a partbased
probabilistic representation [31], we propose a new
3D object...
We propose a family of kernels between images, defined as kernels between their respective segmentation graphs. The kernels are based on soft matching of subtree-patterns of the r...
A new approach to mammographic mass detection is presented in this paper. Although different algorithms have been proposed for such a task, most of them are application dependent....
Handling streams of positional updates from numerous moving objects has become a challenging task for many monitoring applications. Several algorithms have been recently proposed ...