@inproceedings {PUBA260,
	title = {Non-negative Sparse Coding for Motion Extraction},
	author = {Thomas Guthier AND Volker Willert AND Karel Kreuter AND Andrea Schnall AND Julian Eggert},
	year = {2013},
	month = {August},
	abstract = {Visual motion is a rich source of information that
is directly coupled to the underlying shape of a moving object.
One way to describe motion is to use optical flow fields. Due
to the aperture problem, dense optical flow estimation is an illconstraint
problem, while sparse optical flow estimation looses
the shape information of moving objects. Current estimation
algorithms based on regularization or segmentation fail at
surface deformations or when the relevant motion is less
dominant then its sourrounding movements. Both is e.g. true
for face movements, where small movement patterns, so called
action units, need to be preserved for further image analysis.
We present a novel approach to capture the characteristics of
local motion patterns that is based on the brightness constancy
equation of optical flow estimation in combination with feature
extraction using translation invariant non-negative sparse coding.
Our approach simultaneously learns basic motion patterns
and estimates the flow field without requiring pretrained motion
patterns from ground truth optical flow data. We show on a
face expression dataset how this method can preserve weak
movements even in the presence of large head movements.},
	publisher = {IJCNN},
	booktitle = {Int. Joint Conf. on Neural Networks (IJCNN)},
	city = {Dallas, TX, USA}
}