The era of artificial neural network (ANN) began with a simplified application in many fields
and remarkable success in pattern recognition (PR) even in manufacturing industries …

The assignment flow is a smooth dynamical system that evolves on an elementary statistical
manifold and performs contextual data labeling on a graph. We derive and introduce the …

Assignment flows comprise basic dynamical systems for modeling data labeling and related
machine learning tasks in supervised and unsupervised scenarios. They provide adaptive …

We study the inverse problem of model parameter learning for pixelwise image labeling,
using the linear assignment flow and training data with ground truth. This is accomplished by …

Credit risk plays a key role in financial modeling, and financial institutions are required to
incorporate it in their pricing, as well as in capital requirement calculations. A common …

We investigate the problem of pairwise multi-marginal optimal transport, that is, given a
collection of probability distributions $\{P_\alpha\} $ on a Polish space $\mathcal {X} $, to …

Manifold models of image features abound in computer vision. We present a novel approach
that combines unsupervised computation of representative manifold-valued features, called …

We introduce and study the unsupervised self-assignment flow for labeling image data
(euclidean or manifold-valued) without specifying any class prototypes (labels) beforehand …

Gesture recognition is a method for understanding the human body language through
computers. This method bridges the gap between machines and humans more effectively …

The image labeling problem can be described as assigning to each pixel a single element
from a finite set of predefined labels. Recently, a smooth geometric approach for inferring …