A Bayesian marked point process (MPP) model is developed
to detect and count people in crowded scenes. The
model couples a spatial stochastic process governing number
and placem...
In many social settings, images of groups of people are captured. The structure of this group provides meaningful context for reasoning about individuals in the group, and about th...
In deflectometry, the shape of mirror objects is recovered from distorted images of a calibrated scene. While remarkably high accuracies are achievable, state-of-the-art methods ...
Jonathan Balzer, Sebastian Hoefer, Juergen Beyerer
We present the design and implementation of new inexact Newton type Bundle Adjustment algorithms that exploit hardware parallelism for efficiently solving large scale 3D scene re...
Changchang Wu, Sameer Agarwal, Brian Curless, Stev...
The co-occurrence pattern, a combination of binary or local features, is more discriminative than individual features and has shown its advantages in object, scene, and action rec...