%0 Journal Article
%T 从视频到语义：基于知识图谱的视频语义分析技术<br>From Video to Semantic: Video Semantic Analysis Technology Based on Knowledge Graph
%A 邓莉琼
%A 吴吉祥
%A 张丽
%J Computer Science and Application
%P 1584-1590
%@ 2161-881X
%D 2019
%I Hans Publishing
%R 10.12677/CSA.2019.98178
%X <div style=\"text-align:justify;\">
	<span style=\"font-size:14px;\">随着大规模视频的迅猛发展，视频理解受到了广泛的关注，为了填补视频特征与视频理解之间的语义鸿沟，本文提出了一种基于知识图谱的视频语义分析流程，采用了随机漫步方法对视频语义标签信息进行共生性概率的量化，研究了基于知识图谱的视频语义推理技术，相关的实验结果证明了知识图谱方法能有效提高视频语义分析的准确度，构建后的多层次视频语义模型支持在视频分类、视频标注及视频摘要等方面的应用，对媒体语义中的信息组织和知识管理有一定的指导意义。<br />
Video understanding has attracted much research attention especially since the recent availability of large-scale video benchmarks. In order to fill up the semantic gap between video features and understanding, this paper puts forward a video semantic analysis process based on knowledge graph, and adopts random walk to quantify semantic consistency between semantic labels. Then video semantic reasoning based-on knowledge graph is studied. The experimental results prove that knowledge graph can improve semantic understanding effectively. Finally, a constructed multilevel video semantic model supports applications in video classifying, video labeling and video ab-stract, which has some guiding significance for information organization and knowledge management of media semantic.</span> 
</div>
<div style=\"text-align:justify;\">
	<br />
</div>
%K 知识图谱，视频，分类，语义分析<br>Knowledge Graph
%K Video
%K Classify
%K Semantic Analysis
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=31863