Finally, we present an algorithm based on multi-level scene clustering and view-consistent composition.
最后,本文研究了一种基于多层次场景聚类与视点一致性合成的方法。
参考来源 - 基于大位移视图的图像修补技术研究·2,447,543篇论文数据，部分数据来源于NoteExpress
This paper introduced algorithms for video segmentation and scene clustering.
本文介绍了实现视频分割和场景聚类的算法。
This thesis proposes a new effective scene clustering method which can automatically decide the stop point without prior knowledge.
本文提出了一种新的有效的场景聚类算法，无需先验知识，自动决定算法停止点。
Because scenes have much difference in appearance, we adopt unsupervised scene clustering for its universality, which groups video shots with similar visual content into same cluster.
对于视频来说，由于存在较大的场景差异，因此采用无监督的场景聚类，达到通用性的目的。
应用推荐