.png){kind=icon}
返回
An auto-encoder-based summarization algorithm for unstructured videos
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-017-4485-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Video summarization is an effective way to quick view videos and relieve the pressure of videos storage. However the traditional algorithms are hardly adapted to unstructured videos, due to the unobvious for scenes changing and ignoring the structure of the videos. Therefore, an Auto-encoder-based summarization algorithm is proposed in this paper for unstructured videos. Each video structure is detected by an Auto-encoder and both of the interestingness and representativeness of each video segment are predicted by the reconstruction errors of the segment. Meanwhile, most interesting and representative summarization is generated with the limited summary length. The experimental results show that the proposed algorithm obtained a better performance by comparing with the state-of-the-art.
Keyword:
Video summarization
Auto-encoder
Video analysis
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
.png){kind=icon}
Electromagnetic force ripple suppression strategy of the micro permanent magnet linear motor微永磁直线电机电磁力波纹抑制策略
OAAI
OAAI分享收藏分享收藏分享收藏
查看更多内容