We boost the efficiency and robustness of distributionbased matching by random subsampling which results in the minimum number of samples required to achieve a specified probabili...
We introduce a novel topological formulation for contour grouping. Our grouping criterion, called untangling cycles, exploits the inherent topological 1D structure of salient cont...
This paper presents a new method to detect and accurately extract the moving object from a video sequence taken by a hand-held camera. In order to extract the high quality moving ...
Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification m...
Visual surveillance using a camera network has imposed new challenges to camera calibration. An essential problem is that a large number of cameras may not have a common field of ...