Semantic Video Trailers
Harrie Oosterhuis, Sujith Ravi and Michael Bendersky Published in ICML 2016 Workshop on Multi-View Representation Learning (MVRL ’16), 2016. [pdf]
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.
Recommended citation:
H. Oosterhuis, S. Ravi, M. Bendersky. "Query-level Ranker Specialization." In ICML 2016 Workshop on Multi-View Representation Learning. 2016.