Abstract--The goal of image classification is to classify a collection of unlabeled images into a set of semantic classes. Many methods have been proposed to approach this goal by ...
We present an original approach for motion-based retrieval involving partial query. More precisely, we propose an uni ed statistical framework both to extract entities of interest ...
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
“Smart Things” are commonly understood as wireless ad-hoc networked, mobile, autonomous, special purpose computing appliances, usually interacting with their environment impli...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...