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...
Kernel-based objective functions optimized using the mean shift algorithm have been demonstrated as an effective means of tracking in video sequences. The resulting algorithms com...
Gregory D. Hager, Maneesh Dewan, Charles V. Stewar...
The kernel function plays a central role in kernel methods. In this paper, we consider the automated learning of the kernel matrix over a convex combination of pre-specified kerne...
Color-based tracking methods have proved to be efficient for their robustness qualities. The drawback of such global representation of an object is the lack of information on its s...
Our objective is to obtain a state-of-the art object category
detector by employing a state-of-the-art image classifier
to search for the object in all possible image subwindows....
Andrea Vedaldi, Varun Gulshan, Manik Varma, Andrew...