Object identification—the task of deciding that two observed objects are in fact one and the same object—is a fundamental requirement for any situated agent that reasons about...
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
We discuss the need to extend general models and systems for context-awareness to include adaptation of interactions to context. Our approach was motivated by our experiences of de...
In this paper, we propose an automatic method for the objective evaluation of segmentation results. The method is based on computing the deviation of the segmentation results from...
Andrea Cavallaro, Elisa Drelie Gelasca, Touradj Eb...
Having as a main motivation the development of robust and high performing robot vision systems that can operate in dynamic environments, we propose a context-based generic vision s...
Pablo Guerrero, Javier Ruiz-del-Solar, Rodrigo Pal...