This paper introduces an approach for handling complex labelling problems driven by local constraints. The purpose is illustrated by two applications: detection of the road networ...
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...
The ability to distinguish between objects is the fundamental to learning and intelligent behavior in general. The difference between two things is the information we seek; the pr...
Bostjan Brumen, Izidor Golob, Hannu Jaakkola, Tatj...
Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...
This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high...