This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object c...
This paper investigates basic research issues that need to be addressed for developing an architecture that enables repurposing of learning objects in a flexible way. Currently, t...
Katrien Verbert, Dragan Gasevic, Jelena Jovanovic,...
Multi-label learning is useful in visual object recognition when several objects are present in an image. Conventional approaches implement multi-label learning as a set of binary...
Visual dictionaries are widely employed in object recognition to map unordered bags of local region descriptors into feature vectors for image classification. Most visual dictiona...
Recently, in generic object recognition research, a classification technique based on integration of image features is garnering much attention. However, with a classifying techn...