The paper addresses a novel method for realtime analysis of systems with cyclic data flows. The presented method is based on Network Calculus principles, where upper and lower flo...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities ...
—Network coding has been proposed as a technique that can potentially increase the transport capacity of a wireless network via processing and mixing of data packets at intermedi...
Tae-Suk Kim, Serdar Vural, Ioannis Broustis, Dimit...
We present a unifying framework for information theoretic feature selection, bringing almost two decades of research on heuristic filter criteria under a single theoretical inter...
Gavin Brown, Adam Pocock, Ming-Jie Zhao, Mikel Luj...
Deformable model tracking is a powerful methodology that allows us to track the evolution of high-dimensional parameter vectors from uncalibrated monocular video sequences. The co...
Christian Vogler, Siome Goldenstein, Jorge Stolfi,...