We propose a novel approach to designing algorithms for
object tracking based on fusing multiple observation models.
As the space of possible observation models is too large
for...
Object class models trained on hundreds or thousands of
images have shown to enable robust detection. Transferring
knowledge from such models to new object classes trained
from ...
We present a vision-based method that assists human
navigation within unfamiliar environments. Our main contribution
is a novel algorithm that learns the correlation between
use...
We propose a novel consistent max-covering scheme for
human pose estimation. Consistent max-covering formulates
pose estimation as the covering of body part polygons
on an objec...
We present a component-based, trainable system for detecting frontal and near-frontal views of faces in still gray images. The system consists of a two-level hierarchy of Support ...
Bernd Heisele, Thomas Serre, Massimiliano Pontil, ...