CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
一种基于多示例学习的恐怖视频场景识别方法
胡卫明; 王建超; 李兵; 吴偶
2011-11-18
Date Available2012-06-20
CountryCN
Subtype发明
Abstract本发明公开了一种基于多示例学习算法的视频恐怖场景识别方法。该方法包含:对视频场景进行镜头分割和关键帧选取,视频场景对应于多示例学习的“包”,镜头对应“包”中的示例,基于镜头和关键帧分别提取视觉特征、音频特征和颜色情感特征组成特征空间,在特征空间中训练相应的多示例学习分类器;对于一个待测试的视频样本,通过结构化分析,提取相关特征,通过训练的分类器的来预测视频样本的类别:恐怖或非恐怖。本发明提出了一种新的颜色情感特征并把此特征应用到恐怖电影场景识别方法中,该方法具有广阔的应用前景。
Patent NumberCN201110369289.0
Status授权
Document Type专利
Identifierhttp://ir.ia.ac.cn/handle/173211/8603
Collection模式识别国家重点实验室_视频内容安全
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
胡卫明,王建超,李兵,等. 一种基于多示例学习的恐怖视频场景识别方法. CN201110369289.0[P]. 2011-11-18.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[胡卫明]'s Articles
[王建超]'s Articles
[李兵]'s Articles
Baidu academic
Similar articles in Baidu academic
[胡卫明]'s Articles
[王建超]'s Articles
[李兵]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[胡卫明]'s Articles
[王建超]'s Articles
[李兵]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.