Semantic Web Dog Food

Presented at: 19th International World Wide Web Conference (WWW2010)

by Yaxiao Song, Gary Marchionini, Chi Young Oh

With the rapid growth in computing technology and explosive proliferation of digital videos online, it is imperative to give web users effective summarization and skimming tools to facilitate finding and browsing of videos. Video summarization, a mechanism for generating short summaries of videos, has become a common approach for aiding users in browsing and retrieving relevant videos from large video collections. To produce reliable automatic video summarization algorithms, it is essential to first understand how human beings create video summaries with manual efforts. This paper examines a set of video summaries created by multiple human assessors for instructional documentary videos, and identifies the most eye-catching and ear-catching features in these manually generated video summaries. The paper provides insights into what features automatic algorithms should be looking for when performing automatic video summarization.

Keywords: Indexing, retrieval of Web rich-media content

Resource URI on the dog food server: http://data.semanticweb.org/conference/www/2010/paper/main/100

Explore this resource elsewhere:

• on Snorql
• on Sindice
• on dotAC Explorer