The selection of an optical flow method is mostly a choice from among accuracy, efficiency and ease of implementation. While variational approaches tend to be more accurate than lo...
Claudia Nieuwenhuis, Daniel Kondermann, Christoph ...
Image classification is a critical task for both humans and computers. One of the challenges lies in the large scale of the semantic space. In particular, humans can recognize tens...
Learning function relations or understanding structures of data lying in manifolds embedded in huge dimensional Euclidean spaces is an important topic in learning theory. In this ...
nizing multiple forms of information and knowledge processing on different levels of abstraction in a structured and principled manner. We propose knowledge processing middleware a...
It is well known that classical set theory is not expressive enough to adequately model categorization and prototype theory. Recent work on compositionality and concept determinat...