Integrating Web Information to Generate Chinese Video Summaries

Text summarizing is a well-known and developed research topic, which aims to extract the informative sentences to form a small story instead of full document. Traditional text summarization techniques focus on the news article’s summarizing, however, this technique could not apply to video films directly. The video summarization is a newly approach that is able to handle different media types and using text summarization techniques to produce a video summary. In this paper, we proposed a video summarization system that extracts important summaries from a given video via expanding lexical information from web. The experiment show that the integrating web information can help to generate human-readable summary results even the OCR recognition rate is limited.