Multi-view Metric Learning for Multi-view Video Summarization
This addresses the problem of summarizing multi-view videos, which is incremental as it adapts existing metric learning techniques to a new domain.
The paper tackles multi-view video summarization by proposing a multi-view metric learning framework that combines maximum margin clustering with disagreement minimization to exploit redundancy across views, and demonstrates its effectiveness through experiments.
Traditional methods on video summarization are designed to generate summaries for single-view video records; and thus they cannot fully exploit the redundancy in multi-view video records. In this paper, we present a multi-view metric learning framework for multi-view video summarization that combines the advantages of maximum margin clustering with the disagreement minimization criterion. The learning framework thus has the ability to find a metric that best separates the data, and meanwhile to force the learned metric to maintain original intrinsic information between data points, for example geometric information. Facilitated by such a framework, a systematic solution to the multi-view video summarization problem is developed. To the best of our knowledge, it is the first time to address multi-view video summarization from the viewpoint of metric learning. The effectiveness of the proposed method is demonstrated by experiments.