Video co-summarization: Video summarization by visual co-occurrence
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3584-3592
Abstract
We present video co-summarization, a novel perspective to video summarization that exploits visual co-occurrence across multiple videos. Motivated by the observation that important visual concepts tend to appear repeatedly across videos of the same topic, we propose to summarize a video by finding shots that co-occur most frequently across videos collected using a topic keyword. The main technical challenge is dealing with the sparsity of co-occurring patterns, out of hundreds to possibly thousands of irrelevant shots in videos being considered. To deal with this challenge, we developed a Maximal Biclique Finding (MBF) algorithm that is optimized to find sparsely co-occurring patterns, discarding less co-occurring patterns even if they are dominant in one video. Our algorithm is parallelizable with closed-form updates, thus can easily scale up to handle a large number of videos simultaneously. We demonstrate the effectiveness of our approach on motion capture and self-compiled YouTube datasets. Our results suggest that summaries generated by visual co-occurrence tend to match more closely with human generated summaries, when compared to several popular unsupervised techniques.Keywords
This publication has 27 references indexed in Scilit:
- Quasi Real-Time Summarization for Consumer Videos2014
- Ranking Domain-Specific Highlights by Analyzing Edited Videos2014
- CENTRIST: A Visual Descriptor for Scene CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Vlfeat2010
- Unsupervised Object Discovery: A ComparisonInternational Journal of Computer Vision, 2009
- Multi-document video summarization2009
- Nonchronological Video Synopsis and IndexingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Video abstraction: A systematic review and classificationACM Transactions on Multimedia Computing, Communications, and Applications, 2007
- Threading and autodocumenting news videos: a promising solution to rapidly browse news topicsIEEE Signal Processing Magazine, 2006
- Co-clustering documents and words using bipartite spectral graph partitioning2001