首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于上下文信息的新闻故事单元分割
引用本文:冀中,苏育挺,宋星光,纪旭,华蕊.基于上下文信息的新闻故事单元分割[J].天津大学学报(自然科学与工程技术版),2009,42(2):153-158.
作者姓名:冀中  苏育挺  宋星光  纪旭  华蕊
作者单位:天津大学电子信息工程学院,天津,300072  
基金项目:天津市应用基础及前沿技术研究计划重点项目 
摘    要:为了有效检索和管理新闻视频资源,提出了一种利用多模态特征、基于上下文信息的新闻故事单元分割方法。首先利用字幕变化、音频类型和视频镜头类型信息将新闻镜头序列转换成为相应的关键词序列,使新闻故事单元分割转换成为文体序列分割的问题;然后应用一种有效的序列分割模型—条件随机场,来分割新闻故事单元。对多段视频的测试结果证明了该方法的有效性,取得了查全率为72.9%、查准率为88.4%的较好结果。

关 键 词:新闻故事单元分割  上下文信息  条件随机场  视频内容分析  新闻视频

News Story Segmentation Based on Contextual Information
JI Zhong,SU Yu-ting,SONG Xing-guang,JI Xu,HUA Rui.News Story Segmentation Based on Contextual Information[J].Journal of Tianjin University(Science and Technology),2009,42(2):153-158.
Authors:JI Zhong  SU Yu-ting  SONG Xing-guang  JI Xu  HUA Rui
Institution:( School of Electronic Information Engineering, Tianjin University, Tianjin 300072, China)
Abstract:To effectively retrieve and manage news video archive, a news video story segmentation method based on con- textual information was proposed. Firstly, news video shot sequence was transformed into corresponding keyword sequences by using multimodality information, such as caption changing,audio type, and video shot category. And then news video was partitioned into stories with a powerful sequence segmentation model, conditional random fields. The algorithm was applied to multiple test videos, and the test results prove the effectiveness of the method, achieving a better performance with recall of 72.9% and precision of 88.4%.
Keywords:news story segmentation  contextual information  conditional random fields  video content analysis  news video
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号