Paper Info
Title
Real-time summarization of user-generated videos based on semantic recognition
Abstract
User-generated contents play an important role in the Internet video-sharing activities. Techniques for summarizing the user-generated videos (UGVs) into short representative clips are useful in many applications. This paper introduces an approach for UGV summarization based on semantic recognition. Different from other types of videos like movies or broadcasting news, where the semantic contents may vary greatly across different shots, most UGVs have only a single long shot with relatively consistent high-level semantics. Therefore, a few semantically representative segments are generally sufficient for a UGV summary, which can be selected based on the distribution of semantic recognition scores. In addition, due to the poor shooting quality of many UGVs, factors such as camera shaking and lighting condition are also considered to achieve more pleasant summaries. Experiments on over 100 UGVs with both subjective and objective evaluations show that our approach clearly outperforms several alternative methods and is highly efficient. Using a regular laptop, it can produce a summary for a 2-minute video in just 10 seconds.
Year
DOI
Venue
2014
10.1145/2647868.2655013
ACM Multimedia 2001
Keywords
Field
DocType
semantic recognition,user-generated videos,video analysis,video summarization
Computer vision,Automatic summarization,Broadcasting,Laptop,Computer science,Artificial intelligence,Multimedia,Semantics,CLIPS,The Internet
Conference
Citations 
PageRank 
References 
9
0.46
11
Authors
6
Name
Order
Citations
PageRank
Xi Wang155324.14
Yu-Gang Jiang23071152.58
Zhenhua Chai3126.59
Zichen Gu490.46
Xinyu Du590.46
Dong Wang61351186.07