Large-Scale Video Summarization Using Web-Image Priors
Top Cited Papers
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2698-2705
- https://doi.org/10.1109/cvpr.2013.348
Abstract
Given the enormous growth in user-generated videos, it is becoming increasingly important to be able to navigate them efficiently. As these videos are generally of poor quality, summarization methods designed for well-produced videos do not generalize to them. To address this challenge, we propose to use web-images as a prior to facilitate summarization of user-generated videos. Our main intuition is that people tend to take pictures of objects to capture them in a maximally informative way. Such images could therefore be used as prior information to summarize videos containing a similar set of objects. In this work, we apply our novel insight to develop a summarization algorithm that uses the web-image based prior information in an unsupervised manner. Moreover, to automatically evaluate summarization algorithms on a large scale, we propose a framework that relies on multiple summaries obtained through crowdsourcing. We demonstrate the effectiveness of our evaluation framework by comparing its performance to that of multiple human evaluators. Finally, we present results for our framework tested on hundreds of user-generated videos.Keywords
This publication has 21 references indexed in Scilit:
- Automatic evaluation of video summariesACM Transactions on Multimedia Computing, Communications, and Applications, 2012
- SIFT Flow: Dense Correspondence across Scenes and Its ApplicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- I tube, you tube, everybody tubesPublished by Association for Computing Machinery (ACM) ,2007
- The trecvid 2007 BBC rushes summarization evaluation pilotPublished by Association for Computing Machinery (ACM) ,2007
- Webcam Synopsis: Peeking Around the WorldPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- An innovative algorithm for key frame extraction in video summarizationJournal of Real-Time Image Processing, 2006
- Schematic storyboarding for video visualization and editingPublished by Association for Computing Machinery (ACM) ,2006
- Key frame selection by motion analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Maximum matching in a convex bipartite graphNaval Research Logistics Quarterly, 1967