We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
State-of-the-art approaches for detecting filament-like
structures in noisy images rely on filters optimized for signals
of a particular shape, such as an ideal edge or ridge.
W...
We present a new method for detecting interest points
using histogram information. Unlike existing interest point
detectors, which measure pixel-wise differences in image
intens...
Wei-Ting Lee (National Tsing Hua University), Hwan...
We introduce a convex relaxation framework to optimally
minimize continuous surface ratios. The key idea is to minimize
the continuous surface ratio by solving a sequence
of con...
Kalin Kolev (University of Bonn), Daniel Cremers (...
Our goal is to turn an intensity image into its perceived luminance without parsing it into depths, surfaces, or scene illuminations. We start with jarring intensity differences at...