Query-based video summarization is the task of creating a brief visual trailer, which captures the parts of the video (or a collection of videos) that are most relevant to the user-issued query. In this paper, we propose an unsupervised label propagation approach for this task. Our approach effectively captures the multimodal semantics of queries and videos using state-of-the-art deep neural networks and creates a summary that is both semantically coherent and visually attractive. We describe the theoretical framework of our graph-based approach and empirically evaluate its effectiveness in creating relevant and attractive trailers. Finally, we showcase example video trailers generated by our system.
@article{arxiv.1609.01819,
title = {Semantic Video Trailers},
author = {Harrie Oosterhuis and Sujith Ravi and Michael Bendersky},
journal= {arXiv preprint arXiv:1609.01819},
year = {2016}
}