Generation of scalable summaries based on iterative GoP ranking

Video skims and image storyboards are two widely used abstractions for representing the essence of a video sequence, crucial for effective browsing and retrieval applications. In this paper we propose a flexible approach to find a reasonable balance between the semantic coverage and naturalness of the generated summaries, targeting a wide range of summarization ratios. The result of the algorithm is a scalable representation of the information required for summarization (a ranked list of GoPs) with a number of advantages in terms of efficient generation and potential applications.