In this paper we present a novel algorithm for video scene segmentation. We model a scene as a semantically consistent chunk of audio-visual data. Central to the segmentation fram...
A Bayesian marked point process (MPP) model is developed
to detect and count people in crowded scenes. The
model couples a spatial stochastic process governing number
and placem...
Navigation during Minimally Invasive Surgery
(MIS) has recognized difficulties due to limited field-of-view,
off-axis visualization and loss of direct 3D vision. This can cause
...
We facilitate the creation of 3D-looking shaded production drawings from concept sketches. The key to our approach is a class of commonly used construction curves known as cross-s...
Cloud Shao, Adrien Bousseau, Alla Sheffer, Karan S...
We describe how to teach deformable models to maximize image segmentation correctness based on user-specified criteria, and we present a method for evaluating which criteria work ...