HTML documents composed of frames can be difficult to write correctly. We demonstrate a technique that can be used by authors manually creating HTML documents (or by document edit...
Annotations of multimedia documents typically have been pursued in two different directions. Either previous approaches have focused on low level descriptors, such as dominant colo...
We present an approach to spatial inference which is based on the procedural semantics of spatial relations. In contrast to qualitative reasoning, we do not use discrete symbolic m...
Sylvia Wiebrock, Lars Wittenburg, Ute Schmid, Frit...
To enable information integration, schema matching is a critical step for discovering semantic correspondences of attributes across heterogeneous sources. While complex matchings ...
This paper introduces a web image dataset created by NUS’s Lab for Media Search. The dataset includes: (1) 269,648 images and the associated tags from Flickr, with a total of 5,...