计算机应用研究2017，Vol.34Issue(1)：287-289,3.DOI:10.3969/j.issn.1001-3695.2017.01.065
融合视音频特征的影片摘要生成方法
Movie summarization method based on audio-visual feature fusion
摘要
Abstract
This paper proposed a movie summarization method based on audio-visual feature fusion.This method selected vid-eo clips which had close-up faces and atwitter shots as the important clips.To solve the problem of difficulty in movie speech endpoint detection,it introduced a method of speech endpoint detection based on subtitles of motion pictures,which could de-tect the start and end time of captions exactly.Compared with other summarization algorithms,the proposed method is proved to be effective for movie summarization.关键词
视频摘要/人脸检测/端点检测/视音频特征融合Key words
video summarization/face detection/endpoint detection/audio-visual feature fusion分类
信息技术与安全科学引用本文复制引用
栾悉道,谢毓湘,李琛,牛晓..融合视音频特征的影片摘要生成方法[J].计算机应用研究,2017,34(1):287-289,3.基金项目
国家自然科学基金资助项目（61571453）；湖南省自然科学基金资助项目（14JJ3010）；湖南省教育厅重点资助项目 （）
