3 Hits in 4.3 sec

Video shot boundary detection: Seven years of TRECVid activity

Alan F. Smeaton, Paul Over, Aiden R. Doherty
2010 Computer Vision and Image Understanding  
Shot boundary detection (SBD) is the process of automatically detecting the boundaries between shots in video.  ...  In this paper we present an overview of the TRECVid shot boundary detection task, a high-level overview of the most significant of the approaches taken, and a comparison of performances, focussing on one  ...  runs, all exploring techniques for shot boundary detection from video.  ... 
doi:10.1016/j.cviu.2009.03.011 fatcat:w5kluejxi5bfrfrwq7jku7jgda

Content-based video copy detection

Juan Manuel Barrios
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
In particular, Content-Based Video Copy Detection (CBVCD) addresses the need to retrieve videos in a collection that are copies of some original document.  ...  In the case of MUSCLE-VCD-2007, the system outperforms the best published result for that dataset, achieving the maximum detection effectiveness, whereas in the case of TRECVID it shows competitive performance  ...  accuracy at detecting the copy boundaries. • Mean query processing time (MPT): Measures the efficiency at processing the query videos.  ... 
doi:10.1145/1631272.1631539 dblp:conf/mm/Barrios09 fatcat:kpjhi2p3orcsrfi444ewana33i

Video Summarization via Nonlinear Sparse Dictionary Selection

Mingyang Ma, Shaohui Mei, Shuai Wan, Zhiyong Wang, Dagan Feng
2019 IEEE Access  
Video summarization (VS) is to identify important content from a given video, which can help users quickly comprehend video content.  ...  In order to achieve an intuitive and flexible configuration of the VS process, an adaptive criterion, namely energy ratio, is devised to produce video summaries with different lengths for different video  ...  The shot boundary can be detected by identifying changes between of successive frames which implies the boundary.  ... 
doi:10.1109/access.2019.2891834 fatcat:cqll2hqyanaztph6chmxq32ham