Video Summagator: An Interface for Video Summarization and Navigation

Cuong Nguyen, Yuzhen Niu, and Feng Liu

Computer Science Department, Portland State University

Abstract

This paper presents Video Summagator (VS), a volume-based interface for video summarization and navigation. VS models a video as a space-time cube and visualizes the video cube using real-time volume rendering techniques. VS empowers a user to interactively manipulate the video cube. We show that VS can quickly summarize both the static and dynamic video content by visualizing the space-time information in 3D. We demonstrate that VS enables a user to quickly look into the video cube, understand the content, and navigate to the content of interest.

Paper

Cuong Nguyen, Yuzhen Niu, and Feng Liu. Video Summagator: An Interface for Video Summarization and Navigation.  ACM CHI 2012. PDF   Related project Cuong Nguyen and Feng Liu. Gaze-based Notetaking for Learning from Lecture Videos.  ACM CHI 2016. PDF Cuong Nguyen, Wu-chi Feng, and Feng Liu. Hotspot: Making Computer Vision More Effective for Human Video Surveillance.  Information Visualization, 2016. PDF   Cuong Nguyen and Feng Liu. Making Software Tutorial Video Responsive.  ACM CHI 2015. PDF (Best Paper Honorable Mention Award) Cuong Nguyen, Yuzhen Niu, and Feng Liu. Direct Manipulation Video Navigation on Touch Screens.  ACM MobileHCI 2014. PDF   Cuong Nguyen, Yuzhen Niu, and Feng Liu. Direct Manipulation Video Navigation in 3D.  ACM CHI 2013. PDF   (Best Paper Honorable Mention Award)

Demo Video

Acknowledgment The videos from YouTube users, including vcfour3, LIHUTA, WAFELsportsMGMT, iris32com, and skandinaviskman, are used under a Creative Commons license. The Rothman video was downloaded from http://cvg.ethz.ch/research/unstructured-vbr/