Automatic Mid-Level Concepts Clusteringfor Violent Movie Scenes Detection  

作　　者：Terumasa AOKI Shinichi GOTO 

机构地区：[1]New Industry Creation Hatchery Center ~ICHe), Tohoku University, 6-6-10,Aza-Aoba, Aramaki, Aoba-ku, Sendal 9808579,Japan [2]Graduate School of lnformation Sciences (GSIS), Tohoku University, 6-6-10,Aza-Aoba, Aramaki, Aoba-ku, Sendai,9808579, Japan

出　　处：《Journal of Mathematics and System Science》2014年第9期609-619,共11页数学和系统科学（英文版）

摘　　要：This paper presents a novel system for violent scenes detection, which is based on machine learning to handle visual and audio features. MKL （Multiple Kernel Learning） is applied so that multimodality of videos can be maximized. The largest features of our system is that mid-level concepts clustering is proposed and implemented in order to learn mid-level concepts implicitly. By this algorithm, our system does not need manually tagged annotations. The whole system is trained on the dataset from MediaEval 2013 Affect Task and evaluated by its official metric. The obtained results outperformed its best score.

关 键 词：Multimedia analysis video processing violence scenes detection MediaEval machine learning MKL（Multiple KernelLearning） 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TN912.15[自动化与计算机技术—控制科学与工程]