This paper describes a novel appearance based scheme for extraction and representation of video objects. The tracking algorithm used for video object extraction is based upon a ne...
This paper presents a fast algorithm for smooth digital elevation model interpolation and approximation from scattered elevation data. The global surface is reconstructed by subdi...
Joachim Pouderoux, Jean-Christophe Gonzato, Ireneu...
What type of algorithms and statistical techniques support learning from very large datasets over long stretches of time? We address this question through a memory bounded version...
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
Low-rank matrix decompositions are essential tools in the application of kernel methods to large-scale learning problems. These decompositions have generally been treated as black...