首页> 外文OA文献 >Intelligent multimedia indexing and retrieval through multi-source information extraction and merging
【2h】

Intelligent multimedia indexing and retrieval through multi-source information extraction and merging

机译:通过多源信息提取和融合进行智能多媒体索引和检索

摘要

This paper reports work on automated meta-dataudcreation for multimedia content. The approach resultsudin the generation of a conceptual index ofudthe content which may then be searched via semanticudcategories instead of keywords. The noveltyudof the work is to exploit multiple sources ofudinformation relating to video content (in this caseudthe rich range of sources covering important sportsudevents). News, commentaries and web reports coveringudinternational football games in multiple languagesudand multiple modalities is analysed and theudresultant data merged. This merging process leadsudto increased accuracy relative to individual sources.
机译:本文报告了针对多媒体内容的自动元数据增值的工作。该方法导致内容的概念索引的生成,然后可以通过语义 udcategories而不是关键字来搜索内容。这项工作的新颖性是要利用与视频内容有关的多种信息来源(在这种情况下,它涵盖了涵盖重要体育项目的大量来源)。分析,覆盖多种语言的国际足球比赛的新闻,评论和网络报告,以多种方式对国际足球比赛进行分析,合并综合数据。相对于单个来源,此合并过程导致准确性提高。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号