Abstract

It is our pleasure to welcome you to the second TRECVid Video Summarization Workshop, held inconjunction with ACM Multimedia 2008. TRECVid itself is a series of evaluation workshops held each November going back to 2001, in which systems are benchmarked on various video processing tasks in an open, metrics-based forum. Tasks have included search, high-level feature extraction, shot and story boundary determination, copy detection, surveillance event detection, --- and this year, a second take on summarization of BBC rushes video, held separately as this ACM Multimedia workshop. Thirty-one research groups from around the world developed video summarization systems to be tested against 40 rushes videos provided by the BBC Archive. Rushes video is the highly redundant, unedited, raw material from which finished productions are made and represents a largely unused potential source of reusable video material. But how to find out efficiently what material a rushes video contains? Summarization may be part of the solution. The system task was to take each video and automatically compress out redundant and insignificant material to create a summary with duration at most 2% of the original video. Ground truth lists of important segments were created by humans watching the full videos. Each summary was then judged by three humans with respect to how much of the ground truth was included and how well-formed the summary was. The program committee accepted an overview paper and 26 papers from individual participating research groups describing their detailed results and technical approaches, each paper having been reviewed anonymously by 3 reviewers.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.