We present a simple framework to model contextual
relationships between visual concepts. The new framework
combines ideas from previous object-centric methods
(which model conte...
Nikhil Rasiwasia (University Of California, San Di...
We have developed a two-phase generative / discriminative learning procedure for the recognition of classes of objects and concepts in outdoor scenes. Our method uses both multipl...
Classification is one of the basic tasks of data mining in modern database applications including molecular biology, astronomy, mechanical engineering, medical imaging or meteorolo...
Applications that query into very large multidimensional datasets are becoming more common. Many self-describing scientific data file formats have also emerged, which have structu...
In this work semantic features are used to improve the results of the camera selection. These semantic features are group action, person action and person speaking. For this purpo...