: Accurate and efficient video classification demands the fusion of multimodal information and the use of intermediate representations. Combining the two ideas into one framework, ...
In this paper we explore the idea of using high-level semantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the constr...
One of the objectives of ooDBMSs is to use type-speci c methods for manipulating objects, in order to maintain the consistency of the database. This is, however, little help for t...
In this paper, we call the pattern classification problem that consists in assigning a category label to a long audio signal based on its semantic content as Generic Audio Documen...
—Feature-oriented software development (FOSD) aims at the construction, customization, and synthesis of large-scale software systems. We propose a novel software design paradigm,...
Sven Apel, Wolfgang Scholz, Christian Lengauer, Ch...