Comparison and Evaluation of Video Retrieval Approaches Using Query Sentences

Comparison and Evaluation of Video Retrieval Approaches Using Query Sentences
复制标题

DOI:
10.1145/3399637.3399657
复制
发表时间:
2020-04
期刊:
Proceedings of the 2020 2nd International Conference on Intelligent Medicine and Image Processing
影响因子:
--
通讯作者:
K. Ueki;Takayuki Hori
K. Ueki;Takayuki Hori
中科院分区:
其他
文献类型:
--
作者:
K. Ueki;Takayuki Hori

文献摘要

相似文献

以下是使用查询语句从大规模视频数据中检索视频的两种主流方法:(1)找到与查询语句对应的预先训练的概念(例如对象,人,场景和活动)的方法,以及(2)将查询语句和图像/视频映射到同一个特征空间并直接搜索与查询语句匹配的图像/视频的方法。在这项研究中,我们分析了这两种方法的优点和缺点,使用一个大规模的视频数据库的TRECVID基准,并确认这些方法的融合是否可以提高视频检索性能。
Following are two mainstream approaches of video retrieval from large-scale video data using query sentences: (1) an approach to find pre-trained concepts such as objects, persons, scenes, and activities corresponding to a query sentence, and (2) an approach to map a query sentence and images/videos into the same feature space and directly search for images/videos that match the query sentence. In this study, we analyze the advantages and disadvantages of these two approaches using a large-scale video database of TRECVID benchmark and confirm whether the fusion of these approaches can improve video retrieval performance.