While most existing video summarization approaches aim to extract an informative summary of a single video, we propose a novel framework for summarizing multi-view videos by exploiting both intra- and inter-view content correlations in a joint embedding space. We learn the embedding by minimizing an objective function that has two terms: one due to intra-view correlations and another due to inter-view correlations across the multiple views. The solution can be obtained directly by solving one Eigen-value problem that is linear in the number of multi-view videos. We then employ a sparse representative selection approach over the learned embedding space to summarize the multi-view videos. Experimental results on several benchmark datasets demonstrate that our proposed approach clearly outperforms the state-of-the-art.
@article{arxiv.1608.00310,
title = {Video Summarization in a Multi-View Camera Network},
author = {Rameswar Panda and Abir Das and Amit K. Roy-Chowdhury},
journal= {arXiv preprint arXiv:1608.00310},
year = {2016}
}