Abstract—Following the trend of “segmentation for recognition”, we present 2LDA, a novel generative model to automatically segment an image in 2 segments, background and fore...
Alessandro Perina, Marco Cristani, Vittorio Murino
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities ...
The desynchronization approach combines a traditional synchronous specification style with a robust asynchronous implementation model. The main contribution of this paper is the d...
Abhijit Davare, Kelvin Lwin, Alex Kondratyev, Albe...
Abstract. This paper extends a recently proposed model for combinatorial landscapes: Local Optima Networks (LON), to incorporate a first-improvement (greedyascent) hill-climbing a...
Pattern discovery in sequences is an important problem in many applications, especially in computational biology and text mining. However, due to the noisy nature of data, the tra...