This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
A natural consequence of the widespread adoption of XML as standard for information representation and exchange is the redundant storage of large amounts of persistent XML documen...
Abstract. Most information visualisation methods are based on abstract visual representations without any concrete manifestation in the “real world”. However, a variety of abst...
Michael Sedlmair, Kerstin Ruhland, Fabian Hennecke...
Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...