当前位置: X-MOL 学术IEEE Trans. Cybern. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Nystr枚m Approximated Temporally Constrained Multisimilarity Spectral Clustering Approach for Movie Scene Detection
IEEE Transactions on Cybernetics ( IF 9.4 ) Pub Date : 2017-02-07 , DOI: 10.1109/tcyb.2017.2657692
Rameswar Panda , Sanjay K. Kuanar , Ananda S. Chowdhury

Movie scene detection has emerged as an important problem in present day multimedia applications. Since a movie typically consists of huge amount of video data with widespread content variations, detecting a movie scene has become extremely challenging. In this paper, we propose a fast yet accurate solution for movie scene detection using Nystr_m approximated multisimilarity spectral clustering with a temporal integrity constraint. We use multiple similarity matrices to model the wide content variations typically present in any movie dataset. Nystr_m approximation is employed to reduce the high computational cost of constructing multiple similarity measures. The temporal integrity constraint captures the inherent temporal cohesion of the movie shots. Experiments on five movie datasets from different genres clearly demonstrate the superiority of the proposed solution over the state-of-the-art methods.

中文翻译:


用于电影场景检测的 Nyström 近似时间约束多重相似性谱聚类方法



电影场景检测已成为当今多媒体应用中的一个重要问题。由于电影通常包含大量内容变化广泛的视频数据,因此检测电影场景变得极具挑战性。在本文中,我们提出了一种快速而准确的电影场景检测解决方案,使用具有时间完整性约束的 Nystr_m 近似多重相似性谱聚类。我们使用多个相似性矩阵来对任何电影数据集中通常存在的广泛内容变化进行建模。采用 Nystr_m 近似来减少构建多个相似性度量的高计算成本。时间完整性约束捕获了电影镜头固有的时间连贯性。对来自不同类型的五个电影数据集的实验清楚地证明了所提出的解决方案相对于最先进方法的优越性。
更新日期:2017-02-07
down
wechat
bug