Video summarization of timestamp comments videos based on concept of folksonomy

Abstract

Uploading and sharing video has become a populartrend on internet recently. However, it is very difficult to understand which parts of video gain more attentions than other parts. Comment-popping video sharing websites, such as Niconico, is a new kind of emerging video sharing websites. Such websites allows users to input timestamp comments within shared video. This paper proposes two video summarization systems for comment-popping video websites based on the concept of folksonomy. The timestamp comments are analyzed and mined, and then the significant clips are chosen based on the mined information and the frequency of comments or keywords. Hereafter, a summary video is merged from these significant clips.