Image auto-annotation is an important open problem in
computer vision. For this task we propose TagProp, a discriminatively
trained nearest neighbor model. Tags of test
images a...
Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek...
Based on scaling laws describing the statistical structure
of turbulent motion across scales, we propose a multiscale
and non-parametric regularizer for optic-flow estimation.
R...
Patrick H´eas, Etienne M´emin, Dominique Heitz, ...
Conventional stereo matching algorithms assume color constancy on the corresponding opaque pixels in the stereo images. However, when the foreground objects with fractional bounda...
Multi-user collusion is an cost-effective attack against digital fingerprinting, in which a group of attackers collectively undermine the traitor tracing capability of digital fin...
Some of the most successful algorithms for the automated segmentation of images use an Active Regions approach, where a curve is evolved so as to maximize the disparity of its int...
Gregory Randall, Juan Cardelino, Marcelo Bertalm&i...