In this paper we present a video annotation tool based on the LSCOM ontology [2] which contains more than 800 semantic concepts. The tool provides four different ways for the user to locate appropriate concepts to use, namely basic search, search by theme, tree traversal and one which uses pre-computed concept similarities to recommend concepts for the annotator to use. A set of user experiments is reported demonstrating the relative effectiveness of the different approaches.
Type:
Poster / Demo
City:
Athens
Date:
2006-12-06
Department:
Data Science
Eurecom Ref:
2028
Copyright:
© EURASIP. Personal use of this material is permitted. The definitive version of this paper was published in and is available at :
