论文部分内容阅读
多媒体主题搜索指在Web中搜索与主题相关的,并且包含多媒体的网页。目前各大搜索引擎(Google、百度)相继推出了多媒体搜索引擎,主要是利用网页中的相关文本提取描述多媒体信息的关键词进行多媒体信息检索,这种搜索引擎能够直接、快速地从Web中寻找多媒体资源。但所搜索得到的网页往往有大量的重复,根据中国互联网网络信息中心2008年发布的统计报告显示,用户在回答“检索问题时遇到的最大问题”这一提问时,选择“重复信息多”选项的占
Multimedia topic search refers to the web search for topic-related, and contains multimedia pages. At present, major search engines (Google, Baidu) have launched multimedia search engines one after another, mainly using the relevant text in web pages to extract multimedia information to search keywords that describe multimedia information. Such search engines can search directly and quickly from the Web Multimedia resources. However, the web pages searched often have a large number of repetitions. According to the statistical report released by China Internet Network Information Center in 2008, when users answer the question of “the biggest problem encountered in retrieving a question”, they select “repeat Information more ”option accounted for