Classification of TV News Shots with Mining Frequent Frame Composition in News Video Archives
Classification of TV News Shots with Mining Frequent Frame Composition in News Video Archives
批准号:
24650043
负责人:
KATAYAMA Norio
金额:
$2.5万
依托单位国家:
日本
项目类别:
Grant-in-Aid for Challenging Exploratory Research
财政年份:
2012
资助国家:
日本
项目状态:
已结题
起止时间:
2012-04-01 至 2014-03-31
中文摘要
本文的研究目的是对通过跨频道滤波提取的电视新闻镜头进行分类。 跨电视频道过滤是我们以前提出的方法,提取这样的新闻镜头,通常由多个广播公司播出。电视新闻镜头的分类是基于视频帧的组成。 通过自底向上和自顶向下两种方式挖掘新闻视频档案中的频繁帧组合,研究了用于分类的视觉特征。
英文摘要
The aim of our research is to classify TV news shots that are extracted by the cross TV-channel filtering. The cross TV-channel filtering is our formerly proposed method which extracts such news shots that are commonly broadcasted by multiple broadcasters. The classification of TV news shots is based on the video frame composition. With mining frequent frame composition in news video archives both in bottom-up and top-down manners, visual features for the classification have been investigated.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Fine-grained modeling of the conditional selectivity of video features for the enhancement of video retrieval and filtering
-
批准号:18K11386
-
项目类别:Grant-in-Aid for Scientific Research (C)
-
资助金额:$2.83万
-
财政年份:2018
-
负责人:KATAYAMA Norio
-
依托单位:
Test Bed Development for Constructing Video Ontologies from Video Corpora
-
批准号:21300039
-
项目类别:Grant-in-Aid for Scientific Research (B)
-
资助金额:$6.99万
-
财政年份:2009
-
负责人:KATAYAMA Norio
-
依托单位:
Multimedia Database Technologies for Sophisticated Analysis of Large-Scale Video Corpora
-
批准号:18500094
-
项目类别:Grant-in-Aid for Scientific Research (C)
-
资助金额:$2.52万
-
财政年份:2006
-
负责人:KATAYAMA Norio
-
依托单位:
海外基金