Effective bug localization is important for realizing automated debugging. One attractive approach is to apply statistical techniques on a collection of evaluation profiles of pr...
We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguit...
We report on a new framework to investigate the rapid brain development of newborns. It is based on the analysis of depth maps of the cortical surface through the study of a displa...
We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled f...
— In this paper, we introduce a high-speed vision platform, H3 (Hiroshima Hyper Human) Vision, which can simultaneously process a 1024× 1024 pixel image at 1000 fps and a 256× ...