Post-processing Techniques for On-Line Adaptive Video Summarization Based on Relevance Curves

摘要

This paper presents a group of post-processing techniques aimed to on-line adaptive video summary generation based on video analysis curves, named relevance curves obtained by different approaches (e.g., extraction of visual features, semantic features, rate-distortion curves). The developed techniques can be applied to improve the quality of the generated video summaries, control the summaries length and constitute a way to generate summaries with independence of the approach taken to generate the relevance curves that are used as basis for summary generation.