Semantic Video Trailers
This work addresses the problem of generating personalized video summaries for users based on queries, though it appears incremental as it builds on existing graph-based and deep learning methods.
The paper tackles query-based video summarization by proposing an unsupervised label propagation approach that uses deep neural networks to capture multimodal semantics, resulting in semantically coherent and visually attractive video trailers.
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.