Abstract. This paper presents a new framework for the motion segmentation and estimation task on sequences of two grey images without a priori information of the number of moving r...
The IsaLog model and language are presented. The model has complex objects with classes, relations, and isa hierarchies. The language is strongly typed and declarative. The main i...
We present in this paper a novel object tracking system based on 3D contour models. For this purpose, we integrate two complimentary likelihoods, defined on local color statistics...
Abstract: To enable efficient access to multimedia content, the media data has to be augmented by semantic metadata and functionality. The semantic representation has to be integra...
We describe an algorithm for automatically learning discriminative components of objects with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds ...
Bernd Heisele, Thomas Serre, Massimiliano Pontil, ...