Many popular optimization algorithms, like the Levenberg-Marquardt algorithm (LMA), use heuristic-based "controllers" that modulate the behavior of the optimizer during ...
We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and e...
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
In the framework of the interactive search in image databases, we are interested in similarity measures able to learn during the search and usable in real-time. Images are represe...
Justine Lebrun, Sylvie Philipp-Foliguet, Philippe ...
Approaches based on local features and descriptors are increasingly used for the task of object recognition due to their robustness with regard to occlusions and geometrical defor...