论文标题
电影摘要通过稀疏图构造
Movie Summarization via Sparse Graph Construction
论文作者
论文摘要
我们通过创建包含最有用的场景的较短视频来总结全长电影。我们探讨了以下假设：摘要可以通过组装转折点（TPS）的场景（即描述其故事情节的电影中的关键事件）创建。我们提出了一个模型，该模型通过构建代表场景之间关系的稀疏电影图来标识TP场景，并使用多模式信息构建。根据人类法官的说法，与基于序列的模型和通用摘要算法的输出相比，我们方法创建的摘要更具信息和完整，并获得更高的评分。诱导的图是可解释的，为不同的电影类型显示了不同的拓扑。
We summarize full-length movies by creating shorter videos containing their most informative scenes. We explore the hypothesis that a summary can be created by assembling scenes which are turning points (TPs), i.e., key events in a movie that describe its storyline. We propose a model that identifies TP scenes by building a sparse movie graph that represents relations between scenes and is constructed using multimodal information. According to human judges, the summaries created by our approach are more informative and complete, and receive higher ratings, than the outputs of sequence-based models and general-purpose summarization algorithms. The induced graphs are interpretable, displaying different topology for different movie genres.
