Exploiting Temporal and Inter-concept Co-occurrence Structure to Detect High-Level Features in Broadcast Videos

Abstract

In this paper the problem of detecting high-level features from video shots is studied. In particular, we explore the possibility of taking advantage of temporal and interconcept co-occurrence patterns that the high-level features of a video sequence exhibit. Here we present two straightforward techniques for the task: N-gram models and clustering of temporal neighbourhoods. We demonstrate the usefulness of these techniques on data sets of the TRECVID high-level feature detection tasks of the years 2005-2007.