video semantic annotation

基本解释

The semantic retrieval of news video is implemented by the annotation of scene through metadata annotation.
通過引入元數據的標注完成對場景的標注，實現用戶的語義查詢。
In this paper, we discuss the problem of using semi-supervised learning method to do video semantic annotation.
本文討論了利用半監督學習方法進行眡頻語義標注的問題。
At present, most of video semantic annotation methods are based on statistic theory. The methods use supervised learning method to do semantic label.
目前已有的眡頻語義標注方法多是基於統計學理論，採用全監督學習方法進行語義標注工作。