This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
Active contours are adapted to image segmentation by energy minimization. The energies often exhibit local minima, requiring regularization. Such an a priori can be expressed as a...
Eric Debreuve, Michel Barlaud, Jean-Paul Marmorat,...
This paper proposes a general feature selection approach for real-time image matching systems. To demonstrate the idea's effectiveness, we focus on the issue of rotational in...
We present a general Bayesian framework for hyperparameter tuning in L2-regularized supervised learning models. Paradoxically, our algorithm works by first analytically integratin...
In traditional peer-to-peer search networks, operations focus on properly labeled files such as music or video, and the actual search is often limited to text tags. The explosive ...