Automatic construction of multi-video summaries

The ever-growing availability of multimedia data, such as video, creates a strong requirement for efficient tools to manipulate and present this type of data in an effective manner. Automatic summarization is one of those tools. The idea is to automatically and with little or no human interaction creates a short version or subset of key-frames which contains as much information as possible as in the original video. The key issue here is what should be kept in the summary and how can this relevant information be automatically extracted. This paper presents a novel methodology for the automatic construction of video summaries. The work is based on the Simulated User Principle to create and evaluate the quality of a video summary in a way, which is automatic, yet related to user's perception. The method is studied for both the case of single video summaries and the more complex case of summarization involving multi-episode videos. The goal, then becomes not only to describe what is important in a video, but what distinguishes this video from the others. Experimental results are presented to support the proposed ideas.