2010
DOI: 10.1016/j.cviu.2009.03.011
|View full text |Cite
|
Sign up to set email alerts
|

Video shot boundary detection: Seven years of TRECVid activity

Abstract: Shot boundary detection (SBD) is the process of automatically detecting the boundaries between shots in video. It is a problem which has attracted much attention since video became available in digital form as it is an essential pre-processing step to almost all video analysis, indexing, summarisation, search, and other contentbased operations. Automatic SBD was one of the tracks of activity within the annual TRECVid benchmarking exercise, each year from 2001 to 2007 inclusive. Over those seven years we have s… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
143
0
9

Year Published

2010
2010
2018
2018

Publication Types

Select...
5
3
2

Relationship

1
9

Authors

Journals

citations
Cited by 252 publications
(152 citation statements)
references
References 14 publications
0
143
0
9
Order By: Relevance
“…For example in the memory science domain, Zacks et al (2006) notes that "segmenting ongoing activity into distinct events is important for later memory of these events". Meanwhile in the video retrieval community Smeaton et al (2010) suggests that "automatic shot boundary detection is an enabling function for almost all automatic structuring of video". In addition, ' Lin and Hauptmann (2006) state that for lifelogging "continuous recordings need to be segmented into manageable units so that they can be efficiently browsed and indexed'.…”
Section: Identifying Eventsmentioning
confidence: 99%
“…For example in the memory science domain, Zacks et al (2006) notes that "segmenting ongoing activity into distinct events is important for later memory of these events". Meanwhile in the video retrieval community Smeaton et al (2010) suggests that "automatic shot boundary detection is an enabling function for almost all automatic structuring of video". In addition, ' Lin and Hauptmann (2006) state that for lifelogging "continuous recordings need to be segmented into manageable units so that they can be efficiently browsed and indexed'.…”
Section: Identifying Eventsmentioning
confidence: 99%
“…Video search systems have usually concentrated on retrieval at the shot level, with a shot being the smallest unit of a video which still contains temporal information [16]. However not as much attention has been focused on searching for larger/semantic units of retrieval, generally referred to as stories.…”
Section: Introductionmentioning
confidence: 99%
“…Developing effective video shot-boundary detection and keyframe extraction techniques have been a very active sub-topic in the multimedia field since the late 90s and early 2000s and their accuracy level is said to have reached above 95-98% today (for straightforward hard-cut transitions anyway) [29]. We call this a "solved problem" and these well-understood techniques are today featured in many video editing tools to help quickly browse the video contents.…”
Section: Imperfect Back-end Performance and Implicationsmentioning
confidence: 99%