In this paper we describe a multi-strategy approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple fe...
Alexander G. Hauptmann, Ming-yu Chen, Michael G. C...
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
Although Web search engines are targeted towards helping people find new information, people regularly use them to re-find Web pages they have seen before. Researchers have noted ...
The presentation layer of hypermedia systems could benefit from standard object querying functionality and this is most effective if strong typing is enforced. By strong typing we...
We briefly survey several privacy compromises in published datasets, some historical and some on paper. An inspection of these suggests that the problem lies with the nature of the...