Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
Graph construction plays a key role on learning algorithms based on graph Laplacian. However, the traditional graph construction approaches of -neighborhood and k-nearest-neighbor...
When we have a large amount of information, we usually use categories with a hierarchy, in which all information is assigned. This paper proposes a new method of integrating two ca...
In this paper, we propose a new transductive learning framework for image retrieval, in which images are taken as vertices in a weighted hypergraph and the task of image search is...
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 ...