This paper proposes a convolution forest kernel to effectively explore rich structured features embedded in a packed parse forest. As opposed to the convolution tree kernel, the p...
Whereas most existing action recognition methods require computationally demanding feature extraction and/or classification, this paper presents a novel real-time solution that ut...
We explore the problem of detecting whether a device has moved within a room. Our approach relies on comparing summaries of received signal strength measurements over time, which ...
Konstantinos Kleisouris, Bernhard Firner, Richard ...
Classifying network flows by their application type is the backbone of many crucial network monitoring and controlling tasks, including billing, quality of service, security and tr...
Roni Bar-Yanai, Michael Langberg, David Peleg, Lia...
With this paper we offer a game-theoretic perspective for the all-pervasive matching problem in computer vision. Specifically, we formulate the matching problem as a (population) ...