One of the principal bottlenecks in applying learning techniques to classification problems is the large amount of labeled training data required. Especially for images and video, ...
Ajay J. Joshi, Fatih Porikli, Nikolaos Papanikolop...
Concept classification is important to access visual information on the level of objects and scene types. So far, intensity-based features have been widely used. To increase discr...
Koen E. A. van de Sande, Theo Gevers, Cees G. M. S...
We present an algorithm for color classification with explicit illuminant estimation and compensation. A Gaussian classifier is trained with color samples from just one training im...
Autonomous navigation in cross-country environments presents many new challenges with respect to more traditional, urban environments. The lack of highly structured components in t...
Roberto Manduchi, Andres Castano, A. Talukder, Lar...
My thesis aims to contribute towards building autonomous agents that are able to understand their surrounding environment through the use of both audio and visual information. To ...