In extended video sequences, individual frames are grouped into shots which are defined as a sequence taken by a single camera, and related shots are grouped into scenes which are...
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, ...
ons for this project. Most recent ones are listed at the end of this abstract. In the future, feature selection will be integrated in the multi-class EM algorithm to improve the pe...
We propose a kernel-density based scheme that incorporates the object colors with their spatial relevance to track the object in a video sequence. The object is modeled by the col...
Visual sensors provide exclusively uncertain and partial knowledge of a scene. In this article, we present a suitable scene knowledge representation that makes integration and fusi...