Abstract— Recently, classical pairwise Structure From Motion (SfM) techniques have been combined with non-linear global optimization (Bundle Adjustment, BA) over a sliding window...
Javier Civera, Oscar G. Grasa, Andrew J. Davison, ...
With the shift towards chip multiprocessors (CMPs), exploiting and managing parallelism has become a central problem in computer systems. Many issues of parallelism management boi...
Improving the sample efficiency of reinforcement learning algorithms to scale up to larger and more realistic domains is a current research challenge in machine learning. Model-ba...
Commitment-modeled protocols enable flexible and robust interactions among agents. However, existing work has focused on features and capabilities of protocols without considerin...
: Users of front office applications such as call center or customer support applications make millions and millions of decisions each day without analytical support. For example, ...