In many computer vision tasks, scene changes hinder the generalization ability of trained classifiers. For instance, a human detector trained with one set of images is unlikely t...
We propose two fast algorithms for abrupt change detection in streaming data that can operate on arbitrary unknown data distributions before and after the change. The first algor...
BitTorrent is the most popular P2P content delivery application where individual users share various type of content with tens of thousands of other users. The growing popularity ...
The ability of Compressive Sensing (CS) to recover sparse signals from limited measurements has been recently exploited in computational imaging to acquire high-speed periodic and...
M. Salman Asif, Dikpal Reddy, Petros Boufounos, As...
This paper proposes a novel method for handling occluded pixels in stereo images based on a probabilistic voting framework that utilizes a novel support-and-decision process. Occl...