期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于边界归类的新闻视频故事分割算法 被引量：3

News Story Segmentation Based on Boundary Classification
下载PDF
导出
摘要 为有效组织和浏览新闻视频,提出了一种基于边界归类的新闻视频故事分割算法.该算法视镜头边界为候选故事边界,并定义新闻基本处理单元划分新闻视频.算法分为新闻基本处理单元的获取和新闻基本处理单元分析两部分.前者采用镜头分割和镜头标定对原始视频进行合理划分,获取基本处理单元边界,有效缩小故事边界判定范围;后者对基本处理单元内的字幕文本进行分析,实现了字幕文本分类和主题字幕相似性比较,并结合静音特征,从音视频两方面判定故事边界,得到最终的分割结果.实验结果表明,该算法能有效描述新闻故事边界,准确分割新闻故事单元,实现对新闻视频的语义划分,为新闻视频检索、导航等应用提供前期辅助. In order to organize and browse news video, a story segmentation scheme based on boundary classification was proposed. The proposed scheme regarded shot boundaries as candidate story boundaries, and defined news basic unit to divide the news video. The scheme can be divided into news basic unit gain and news basic unit analysis. The former narrows the story boundaries by using shot segmentation and shot demarcation while the latter gains the final segmentation result by analyzing the caption in news, achieving the classification of caption and comparison of topic caption, by combining with silence feature. The experimental results show that the proposed scheme can express story boundaries effectively, divide the news into story unit precisely and realize news video semantic partition, which can provide convenience to news retrieval and news indexing.
作者 王娟 蒋兴浩 孙锬锋
机构地区 上海交通大学电子信息与电气工程学院 上海交通大学信息内容分析技术国家工程实验室
出处 《上海交通大学学报》 EI CAS CSCD 北大核心 2016年第9期1384-1389,1398,共7页 Journal of Shanghai Jiaotong University
基金 国家自然科学基金项目(61272439 61272239 61572320 61572321) 教育部博士点专项基金项目(20120073110053)
关键词 新闻故事分割 新闻基本处理单元 镜头边界 主题字幕 静音检测 news story segmentation news basic unit shot boundary topic caption silence detection
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献12

  • 1NIST. Guidelines for the TRECVID 2003 evaluation [EP/OL]. (2004-06-15) [2015-09-11]. http: //www-nlpir, nist. gov/projects/tv2003/tv2003, html.
  • 2MA Chengyuan, BYUNGKI Byun, KIM I, etal. A detection-based approach to broadcast news video sto- ry segmentation[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. Taipei: IEEE, 2009 : 1957-1960.
  • 3LU Mimi, XIE Lei, FU Zhonghua, etal. Multi-mo- dal feature integration for story boundary detection in broadcast news[C]//The 7th International Symposium on Chinese Spoken Language Processing. Tainan: IEEE, 2010:420-425.
  • 4SONG Yu, WANG Wenhong, GUO Feng]uan. News story segmentation based on audio-visual features fu- sion[C]//The 4 th International Conference on Com- puter Science & Education. Nanning: IEEE, 2009: 1065-1068.
  • 5XU Su, FENG Bailan, XU Bo. Multi-modal topic u- nit segmentation in videos using conditional random fields[C]//IEEE International Conference on Acous- tics, Speech and Signal Processing. Vancouver B C: IEEE, 2013: 2287-2291.
  • 6FENG Bailan, CHEN Zhineng, ZHENG Rong, et al. Multiple style exploration for story unit segmen- tation of broadcast news video[J]. Multimedia Sys- tems, 2013, 20(4): 347-361.
  • 7Daneshi M, Vajda P, CHEN D M, et al. Eigne- news: Generating and delivering persormlized news yideo[C]///IEEE International Conference on Multi- media and Expo Workshops. San Jose: IEEE, 2013: 1-6.
  • 8CHEN D M, VAJDA P, TSAI S S, et al. Analysis of visual similarity in news videos with robust and memory-efficient image retrieval[C]//IEEE Interna- tional Conference on Multimedia and Expo Workshops. San Jose: IEEE, 2013: 1-6.
  • 9冀中,张春田,苏育挺.新闻视频故事单元分割技术综述[J].中国图象图形学报,2007,12(11):1952-1960. 被引量：9
  • 10ZHAO Xu, LIN from corners: A KaiHsing, FU novel approach Yun, et al. Text to detect text andcaption in videos [J]. IEEE Transactions on Image Processing, 2011, 20(3): 790-799.

二级参考文献33

  • 1Lu L,Zhang H J,Li S Z.Content-based audio classification and segmentation by using support vector machines[J].Multimedia Systems,2003,8(6):482-492.
  • 2Hanjalic A,Lagensijk R L,Biemond J.Template-based detection of anchorperson shots in news programs[A].In:Proceedings of International Conference on Image Processing[C],Chicago,IL,US,1998:148-152.
  • 3Gao X B,Li J,Yang B.A graph-theoretical clustering based anchorperson shot detection for news video indexing[A].In:International Conference on Computational Intelligence and Multimedia Applications[C],Xi'an,China,2003:108-113.
  • 4Hsu W,Chang S F.Generative,discriminative,and ensemble learning on multi-modal perceptual fusion toward news video story segmentation[A].In:Proceedings of IEEE International Conference on Multimedia and Expo[C].Taipei,China,2006:1091-1094.
  • 5Shriberg E,Stolcke A,Hakkani-Tur D,et al.Prosody-based automatic segmentation of speech into sentences and topics[J].Speech Communication,2000,32(1):127-154.
  • 6Eichmann D,Park D J.Experiments in Boundaries Recognition at the University of Iowa[EB/OL].http://www.itl.nist.gov/iaui/894.02/projeets/tvpubs/tvpapers03/uiowa.paper.pdf.
  • 7Wang C,Wang Y,Liu H Y,et al.Automatic story segmentation of news video based on audio-visual features and text information[A].In:Proceedings of International Conference on Machine Learning and Cybernetics[C],Xi'an,China,2003:3008-3011.
  • 8Qi W,Gu L,Jiang H,et al.Integrating visual,audio and text analysis for news video[A].In:Proceedings of International Conference on Mage Processing[C],Vancouver,BC,Canada,2000:520-523.
  • 9Lan D J,Ma Y F,Zhang H J.Multi-level anchorperson detection using multimodal association[A].In:Proceedings of International Conference on Pattern Recognition[C],Cambridge,UK,2004:890-893.
  • 10Chua T S,Chang S F,Chaisorn L,et al.Story Boundary Detection in Large Broadcast News Video Archives-Techniques,Experience and Trends[A].In:Proceedings of ACM Multimedia ' 2004[C].New York,US,2004:656-659.

共引文献8

同被引文献13

引证文献3

二级引证文献2

上海交通大学学报
2016年 第9期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部