因此，如何进行有效的视频语义标注是本文研究的目的。
So, how to do video annotation efficiently is the purpose of this paper.
本文讨论了利用半监督学习方法进行视频语义标注的问题。
In this paper, we discuss the problem of using semi-supervised learning method to do video semantic annotation.
目前已有的视频语义标注方法多是基于统计学理论，采用全监督学习方法进行语义标注工作。
At present, most of video semantic annotation methods are based on statistic theory. The methods use supervised learning method to do semantic label.
文中采用统计学理论，利用贝叶斯概率公式计算视频语义出现的概率，选取概率最大的类别标注未标记的样本。
In the paper, we use the statistical theory to calculate the probability of video semantics by Bayesian formula, choose the semantic of maximal probability to label the unlabeled samples.
多媒体自动概念标注是在语义层次上进行视频浏览、搜索的关键技术。
Automatically annotating concepts for multimedia is a key to semantic-level video browsing, search and navigation.
多媒体自动概念标注是在语义层次上进行视频浏览、搜索的关键技术。
Automatically annotating concepts for multimedia is a key to semantic-level video browsing, search and navigation.
应用推荐