We describe an original method for selecting key frames to represent the content of every shot in a video. We aim at spatially sampling in an uniform way the coverage of the scene ...
Brigitte Fauvet, Patrick Bouthemy, Patrick Gros, F...
We propose an approach to categorize real-world natural scenes based on a semantic typicality measure. The proposed typicality measure allows to grade the similarity of an image wi...
We describe a novel method for human detection in single images which can detect full bodies as well as close-up views in the presence of clutter and occlusion. Humans are modeled ...
Krystian Mikolajczyk, Cordelia Schmid, Andrew Ziss...
There is a growing interest in the use of UML class diagrams as a modeling language to represent domain ontologies. In a series of papers (e.g., [1,2]) we have been using the Gener...
Any non-trivial top-level ontology should take temporal notions into account. The details of how this should be done, however, are frequently debated. In this paper it is argued th...