Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called...
Point sets obtained from computer vision techniques are often noisy and non-uniform. We present a new method of surface reconstruction that can handle such data sets using anisotr...
We present a new method of computing invariants in videos captured from different views to achieve view-invariant action recognition. To avoid the constraints of collinearity or c...
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...
Conventional contour tracking algorithms with level set often use generative models to construct the energy function. For tracking through cluttered and noisy background, however,...