Although many spatio-temporal conceptual models has been proposed in the last years, users must express their queries on the underlying physical data structures. In the context of ...
Analyzing videos of human activities involves not only recognizing actions (typically based on their appearances), but also determining the story/plot of the video. The storyline ...
Feature selection for video retrieval applications is impractical with existing techniques, because of their high time complexity and their failure on the relatively sparse trainin...
We demonstrate MMS, a system for storing and managing a variety of metadata in a simple, elegant and uniform way. The system is based on two observations. First, that the relation...
Abstract. Different strategies to learn user semantic queries from dissimilarity representations of video audio-visual content are presented. When dealing with large corpora of vi...