Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
As metadata is often not sufficiently provided by authors of Learning Resources, automatic metadata generation methods are used to create metadata afterwards. One kind of metadata ...
Medical learning objects deviates from traditional notion of learning object in that it is always in a digital form and relates to medication. They may include text, images, sound...
People often recognize 3D objects by their boundary shape. Designing an algorithm for such a task is interesting and useful for retrieving objects from a shape database. In this pa...
This paper presents a robust and efficient skeleton-based graph matching method for object recognition and recovery applications. The novel feature is to unify both object recogni...