In this paper we propose a new approach for semi-supervised structured output learning. Our approach uses relaxed labeling on unlabeled data to deal with the combinatorial nature ...
Paramveer S. Dhillon, S. Sathiya Keerthi, Kedar Be...
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
We propose a method that dramatically improves the performance of template-based matching in terms of size of convergence region and computation time. This is done by selecting a ...
Selim Benhimane, Alexander Ladikos, Vincent Lepeti...
Traditional snakes, or active contours, are planar parametric curves. Their parameters are determined by optimizing the weighted sum of three energy terms: one depending on the dat...
With energy consumption becoming one of the first-class optimization parameters in computer system design, compilation techniques that consider performance and energy simultaneous...