The CPR model for summarizing video

Marat Fayzullin; V. S. Subrahmanian; Antonio Picariello; Maria Luisa Sapino

doi:10.1007/s11042-005-0451-7

The CPR model for summarizing video

Marat Fayzullin, V. S. Subrahmanian, Antonio Picariello, Maria Luisa Sapino

Research output: Contribution to journal › Article › peer-review

12 Scopus citations

Abstract

Most past work on video summarization has been based on selecting key frames from videos. We propose a model of video summarization based on three important parameters: Priority (of frames), Continuity (of the summary), and non-Repetition (of the summary). In short, a summary must include high priority frames and must be continuous and non-repetitive. An optimal summary is one that maximizes an objective function based on these three parameters. We show examples of how CPR parameters can be computed and provide algorithms to find optimal summaries based on the CPR approach. Finally, we briefly report on the performance of these algorithms.

Original language	English (US)
Pages (from-to)	153-173
Number of pages	21
Journal	Multimedia Tools and Applications
Volume	26
Issue number	2
DOIs	https://doi.org/10.1007/s11042-005-0451-7
State	Published - Jun 2005
Externally published	Yes

Keywords

Algorithms
Databases
Framework
Multimedia
Summarization
Video

ASJC Scopus subject areas

Software
Media Technology
Hardware and Architecture
Computer Networks and Communications

Access to Document

10.1007/s11042-005-0451-7

Cite this

@article{103c419fb12644fc877870d558dbcc6c,

title = "The CPR model for summarizing video",

abstract = "Most past work on video summarization has been based on selecting key frames from videos. We propose a model of video summarization based on three important parameters: Priority (of frames), Continuity (of the summary), and non-Repetition (of the summary). In short, a summary must include high priority frames and must be continuous and non-repetitive. An optimal summary is one that maximizes an objective function based on these three parameters. We show examples of how CPR parameters can be computed and provide algorithms to find optimal summaries based on the CPR approach. Finally, we briefly report on the performance of these algorithms.",

keywords = "Algorithms, Databases, Framework, Multimedia, Summarization, Video",

author = "Marat Fayzullin and Subrahmanian, {V. S.} and Antonio Picariello and Sapino, {Maria Luisa}",

note = "Funding Information: Work supported in part by ARO grant DAAD190310202, ARL grants DAAD190320026 and DAAL0197K0135, the ARL CTAs on Telecommunications and Advanced Decision Architectures, and NSF grants IIS0329851 and 0205489.",

year = "2005",

month = jun,

doi = "10.1007/s11042-005-0451-7",

language = "English (US)",

volume = "26",

pages = "153--173",

journal = "Multimedia Tools and Applications",

issn = "1380-7501",

publisher = "Springer Netherlands",

number = "2",

}

TY - JOUR

T1 - The CPR model for summarizing video

AU - Fayzullin, Marat

AU - Subrahmanian, V. S.

AU - Picariello, Antonio

AU - Sapino, Maria Luisa

N1 - Funding Information: Work supported in part by ARO grant DAAD190310202, ARL grants DAAD190320026 and DAAL0197K0135, the ARL CTAs on Telecommunications and Advanced Decision Architectures, and NSF grants IIS0329851 and 0205489.

PY - 2005/6

Y1 - 2005/6

N2 - Most past work on video summarization has been based on selecting key frames from videos. We propose a model of video summarization based on three important parameters: Priority (of frames), Continuity (of the summary), and non-Repetition (of the summary). In short, a summary must include high priority frames and must be continuous and non-repetitive. An optimal summary is one that maximizes an objective function based on these three parameters. We show examples of how CPR parameters can be computed and provide algorithms to find optimal summaries based on the CPR approach. Finally, we briefly report on the performance of these algorithms.

AB - Most past work on video summarization has been based on selecting key frames from videos. We propose a model of video summarization based on three important parameters: Priority (of frames), Continuity (of the summary), and non-Repetition (of the summary). In short, a summary must include high priority frames and must be continuous and non-repetitive. An optimal summary is one that maximizes an objective function based on these three parameters. We show examples of how CPR parameters can be computed and provide algorithms to find optimal summaries based on the CPR approach. Finally, we briefly report on the performance of these algorithms.

KW - Algorithms

KW - Databases

KW - Framework

KW - Multimedia

KW - Summarization

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=21244477497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21244477497&partnerID=8YFLogxK

U2 - 10.1007/s11042-005-0451-7

DO - 10.1007/s11042-005-0451-7

M3 - Article

AN - SCOPUS:21244477497

SN - 1380-7501

VL - 26

SP - 153

EP - 173

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

IS - 2

ER -

The CPR model for summarizing video

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this