Semantic Retrieval in a Large-Scale Video Database by Using Both Image and Text Feature

Semantic Retrieval in a Large-Scale Video Database by Using Both Image and Text Feature
复制标题

利用图像和文本特征进行大规模视频数据库的语义检索

DOI:
10.1007/978-3-540-30542-2_95
复制
发表时间:
2004
期刊:
Pacific Rim Conference on Multimedia
影响因子:
--
通讯作者:
S. Asano
S. Asano
中科院分区:
--
文献类型:
--
作者:
Chuan Yu;Hiroshi Mo;Norio Katayama;S. Satoh;S. Asano

文献摘要

被引文献

相似文献

本文提出了一种将视频数据中的图像特征与文本信息相结合的检索方法。我们不仅比较图像的相似度,而且通过使用文本关键字搜索来预先缩小检索集。用户输入也在提高检索准确率方面起着关键作用。
The paper demonstrates a new retrieval method of intergrating both image features and text informations derived from video data. We compare not only image similiarity, also narrow the retrieval sets in advance by employing searching in text keywords. Users inputs also performs the key role in improving retrieval accuracy.