We propose an unconventional but highly effective approach
to robust fitting of multiple structures by using statistical
learning concepts. We design a novel Mercer kernel
for t...
This paper addresses the problem of automatic temporal
annotation of realistic human actions in video using mini-
mal manual supervision. To this end we consider two asso-
ciate...
Olivier Duchenne, Ivan Laptev, Josef Sivic, Franci...
To utilize CT or MRI images for computer aided diagnosis applications, robust features that represent 3-D image data need to be constructed and subsequently used by a classificati...
We propose a novel classification approach for automatically detecting pulmonary embolism (PE) from computedtomography-angiography images. Unlike most existing approaches that req...
Texture information in images is coupled with geometric macrostructures and piecewise-smooth intensity variations. Decomposing an image f into a geometric structure component u an...