通过例子视频进行视频检索的新方法

结合作者开发的系统，提出了一种新的视频相似度度量模型，详细地介绍了算法的实现，并得出了实验结果。相对于已有的算法，它在考虑人们主观视觉判断的基础上，提出了许多影响相似度的因子，如顺序因子、速度因子、干扰因子等。因而它全面、系统地体现了视频间的相似程度。而且该算法具有粒度可适性，可用于不同层次的视频结构的比较，在视频检索系统中。它可以广泛地应用于针对用户提交例子的查询中。

A New Approach to Retrieve Video by Example Video Clip

The similarity measure of two video clips is the key issue to video retrieval. In the development of video retrieval system, a new model of video similarity is proposed. Contrasting with existing algorithms, it presents many influencing factors, such as order factor, speed factor, interfere factor, etc, on the basis of human's subjective visual judgement. So this algorithm embodies the degree of similarity completely and systematically. On the other hand, it has resolution adaptation because it can be applied on every level of video structure. In the retrieval system, it can be used to process video query by example clip successfully. This paper introduces this algorithm in detail and presents experiment results at the end of the paper.