A domain-independent and personalized video abstraction algorithm

Jinguk Jeong, Jongho Nang, Hojung Cha

Research output: Contribution to journalArticle

Abstract

A video server on the Internet usually provides a short version of a video clip, a video abstraction, in order to provide highlights or the overall story to users as quickly as possible. However, since it is statically generated by content providers using domain-dependent heuristics, it cannot satisfy all users simultaneously. This paper proposes a domain-independent video abstraction algorithm that generates various video abstractions dynamically according to the users' requirements. It first identifies some low-level visual and temporal constraints that a good video abstraction should satisfy domain-independently, such as that it should be well-distributed, highly-active, and non-duplicated (or concise), that are used to partially represent the user's requirements. These constraints are formalized as objective functions, and a simulated annealing algorithm is used to find a set of shots that maximizes the weighted sum of these objective functions as much as possible. It is a personalized abstraction algorithm since each user can generate and view various video abstractions by dynamically adjusting the weights of the constraints. From the results of several experiments with a Korean movie and other well-known movie videos, we found that the proposed algorithm can produce various useful video abstractions very quickly.

Original languageEnglish
Pages (from-to)1183-1196
Number of pages14
JournalJournal of Information Science and Engineering
Volume20
Issue number6
Publication statusPublished - 2004 Nov 1

Fingerprint

abstraction
video
movies
Simulated annealing
Servers
Internet
video clip
heuristics
Experiments
experiment

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Hardware and Architecture
  • Library and Information Sciences
  • Computational Theory and Mathematics

Cite this

@article{d51dad2780154f6096202de7d2b86060,
title = "A domain-independent and personalized video abstraction algorithm",
abstract = "A video server on the Internet usually provides a short version of a video clip, a video abstraction, in order to provide highlights or the overall story to users as quickly as possible. However, since it is statically generated by content providers using domain-dependent heuristics, it cannot satisfy all users simultaneously. This paper proposes a domain-independent video abstraction algorithm that generates various video abstractions dynamically according to the users' requirements. It first identifies some low-level visual and temporal constraints that a good video abstraction should satisfy domain-independently, such as that it should be well-distributed, highly-active, and non-duplicated (or concise), that are used to partially represent the user's requirements. These constraints are formalized as objective functions, and a simulated annealing algorithm is used to find a set of shots that maximizes the weighted sum of these objective functions as much as possible. It is a personalized abstraction algorithm since each user can generate and view various video abstractions by dynamically adjusting the weights of the constraints. From the results of several experiments with a Korean movie and other well-known movie videos, we found that the proposed algorithm can produce various useful video abstractions very quickly.",
author = "Jinguk Jeong and Jongho Nang and Hojung Cha",
year = "2004",
month = "11",
day = "1",
language = "English",
volume = "20",
pages = "1183--1196",
journal = "Journal of Information Science and Engineering",
issn = "1016-2364",
publisher = "Institute of Information Science",
number = "6",

}

A domain-independent and personalized video abstraction algorithm. / Jeong, Jinguk; Nang, Jongho; Cha, Hojung.

In: Journal of Information Science and Engineering, Vol. 20, No. 6, 01.11.2004, p. 1183-1196.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A domain-independent and personalized video abstraction algorithm

AU - Jeong, Jinguk

AU - Nang, Jongho

AU - Cha, Hojung

PY - 2004/11/1

Y1 - 2004/11/1

N2 - A video server on the Internet usually provides a short version of a video clip, a video abstraction, in order to provide highlights or the overall story to users as quickly as possible. However, since it is statically generated by content providers using domain-dependent heuristics, it cannot satisfy all users simultaneously. This paper proposes a domain-independent video abstraction algorithm that generates various video abstractions dynamically according to the users' requirements. It first identifies some low-level visual and temporal constraints that a good video abstraction should satisfy domain-independently, such as that it should be well-distributed, highly-active, and non-duplicated (or concise), that are used to partially represent the user's requirements. These constraints are formalized as objective functions, and a simulated annealing algorithm is used to find a set of shots that maximizes the weighted sum of these objective functions as much as possible. It is a personalized abstraction algorithm since each user can generate and view various video abstractions by dynamically adjusting the weights of the constraints. From the results of several experiments with a Korean movie and other well-known movie videos, we found that the proposed algorithm can produce various useful video abstractions very quickly.

AB - A video server on the Internet usually provides a short version of a video clip, a video abstraction, in order to provide highlights or the overall story to users as quickly as possible. However, since it is statically generated by content providers using domain-dependent heuristics, it cannot satisfy all users simultaneously. This paper proposes a domain-independent video abstraction algorithm that generates various video abstractions dynamically according to the users' requirements. It first identifies some low-level visual and temporal constraints that a good video abstraction should satisfy domain-independently, such as that it should be well-distributed, highly-active, and non-duplicated (or concise), that are used to partially represent the user's requirements. These constraints are formalized as objective functions, and a simulated annealing algorithm is used to find a set of shots that maximizes the weighted sum of these objective functions as much as possible. It is a personalized abstraction algorithm since each user can generate and view various video abstractions by dynamically adjusting the weights of the constraints. From the results of several experiments with a Korean movie and other well-known movie videos, we found that the proposed algorithm can produce various useful video abstractions very quickly.

UR - http://www.scopus.com/inward/record.url?scp=9944249988&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9944249988&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:9944249988

VL - 20

SP - 1183

EP - 1196

JO - Journal of Information Science and Engineering

JF - Journal of Information Science and Engineering

SN - 1016-2364

IS - 6

ER -