Abstract. We analyze the expected cost of a greedy active learning algorithm. Our analysis extends previous work to a more general setting in which different queries have differe...
Dynamical shape priors are curical for level set-based nonrigid object tracking with noise, occlusions or background clutter. In this paper, we propose a level set tracking framew...
In this paper, we propose an Active Learning (AL) framework for the Multi-Task Adaptive Filtering (MTAF) problem. Specifically, we explore AL approaches to rapidly improve an MTAF...
Implementing and maintaining complicated manufacturing processes in an error-free mode is essential to the survival of any manufacturing business. One essential element to realizi...
We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this ...