ClassView

Hierarchical video shot classification, indexing, and accessing

Jianping Fan, Ahmed Elmagarmid, Xingquan Zhu, Walid G. Aref, Lide Wu

Research output: Contribution to journalArticle

104 Citations (Scopus)

Abstract

Recent advances in digital video compression and networks have made video more accessible than ever. However, the existing content-based video retrieval systems still suffer from the following problems. 1 ) Semantics - sensitive video classification problem because of the semantic gap between low-level visual features and high-level semantic visual concepts; 2) Integrated video access problem because of the lack of efficient video database indexing, automatic video annotation, and concept-oriented summary organization techniques. In this paper, we have proposed a novel framework, called ClassView, to make some advances toward more efficient video database indexing and access. 1) A hierarchical semantics-sensitive video classifier is proposed to shorten the semantic gap. The hierarchical tree structure of the semantics-sensitive video classifier is derived from the domain-dependent concept hierarchy of video contents in a database. Relevance analysis is used for selecting the discriminating visual features with suitable importances. The Expectation-Maximization (EM) algorithm is also used to determine the classification rule for each visual concept node in the classifier. 2) A hierarchical video database indexing and summary presentation technique is proposed to support more effective video access over a large-scale database. The hierarchical tree structure of our video database indexing scheme is determined by the domain-dependent concept hierarchy which is also used for video classification. The presentation of visual summary is also integrated with the inherent hierarchical video database indexing tree structure. Integrating video access with efficient database indexing tree structure has provided great opportunity for supporting more powerful video search engines.

Original languageEnglish
Pages (from-to)70-86
Number of pages17
JournalIEEE Transactions on Multimedia
Volume6
Issue number1
DOIs
Publication statusPublished - 1 Feb 2004
Externally publishedYes

Fingerprint

Semantics
Classifiers
Automatic indexing
Search engines
Image compression

Keywords

  • Video classification
  • Video database indexing
  • Video retrieval
  • Visual summarization

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

ClassView : Hierarchical video shot classification, indexing, and accessing. / Fan, Jianping; Elmagarmid, Ahmed; Zhu, Xingquan; Aref, Walid G.; Wu, Lide.

In: IEEE Transactions on Multimedia, Vol. 6, No. 1, 01.02.2004, p. 70-86.

Research output: Contribution to journalArticle

Fan, Jianping ; Elmagarmid, Ahmed ; Zhu, Xingquan ; Aref, Walid G. ; Wu, Lide. / ClassView : Hierarchical video shot classification, indexing, and accessing. In: IEEE Transactions on Multimedia. 2004 ; Vol. 6, No. 1. pp. 70-86.
@article{c5e7696190354546bb03a12d62f05376,
title = "ClassView: Hierarchical video shot classification, indexing, and accessing",
abstract = "Recent advances in digital video compression and networks have made video more accessible than ever. However, the existing content-based video retrieval systems still suffer from the following problems. 1 ) Semantics - sensitive video classification problem because of the semantic gap between low-level visual features and high-level semantic visual concepts; 2) Integrated video access problem because of the lack of efficient video database indexing, automatic video annotation, and concept-oriented summary organization techniques. In this paper, we have proposed a novel framework, called ClassView, to make some advances toward more efficient video database indexing and access. 1) A hierarchical semantics-sensitive video classifier is proposed to shorten the semantic gap. The hierarchical tree structure of the semantics-sensitive video classifier is derived from the domain-dependent concept hierarchy of video contents in a database. Relevance analysis is used for selecting the discriminating visual features with suitable importances. The Expectation-Maximization (EM) algorithm is also used to determine the classification rule for each visual concept node in the classifier. 2) A hierarchical video database indexing and summary presentation technique is proposed to support more effective video access over a large-scale database. The hierarchical tree structure of our video database indexing scheme is determined by the domain-dependent concept hierarchy which is also used for video classification. The presentation of visual summary is also integrated with the inherent hierarchical video database indexing tree structure. Integrating video access with efficient database indexing tree structure has provided great opportunity for supporting more powerful video search engines.",
keywords = "Video classification, Video database indexing, Video retrieval, Visual summarization",
author = "Jianping Fan and Ahmed Elmagarmid and Xingquan Zhu and Aref, {Walid G.} and Lide Wu",
year = "2004",
month = "2",
day = "1",
doi = "10.1109/TMM.2003.819583",
language = "English",
volume = "6",
pages = "70--86",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - ClassView

T2 - Hierarchical video shot classification, indexing, and accessing

AU - Fan, Jianping

AU - Elmagarmid, Ahmed

AU - Zhu, Xingquan

AU - Aref, Walid G.

AU - Wu, Lide

PY - 2004/2/1

Y1 - 2004/2/1

N2 - Recent advances in digital video compression and networks have made video more accessible than ever. However, the existing content-based video retrieval systems still suffer from the following problems. 1 ) Semantics - sensitive video classification problem because of the semantic gap between low-level visual features and high-level semantic visual concepts; 2) Integrated video access problem because of the lack of efficient video database indexing, automatic video annotation, and concept-oriented summary organization techniques. In this paper, we have proposed a novel framework, called ClassView, to make some advances toward more efficient video database indexing and access. 1) A hierarchical semantics-sensitive video classifier is proposed to shorten the semantic gap. The hierarchical tree structure of the semantics-sensitive video classifier is derived from the domain-dependent concept hierarchy of video contents in a database. Relevance analysis is used for selecting the discriminating visual features with suitable importances. The Expectation-Maximization (EM) algorithm is also used to determine the classification rule for each visual concept node in the classifier. 2) A hierarchical video database indexing and summary presentation technique is proposed to support more effective video access over a large-scale database. The hierarchical tree structure of our video database indexing scheme is determined by the domain-dependent concept hierarchy which is also used for video classification. The presentation of visual summary is also integrated with the inherent hierarchical video database indexing tree structure. Integrating video access with efficient database indexing tree structure has provided great opportunity for supporting more powerful video search engines.

AB - Recent advances in digital video compression and networks have made video more accessible than ever. However, the existing content-based video retrieval systems still suffer from the following problems. 1 ) Semantics - sensitive video classification problem because of the semantic gap between low-level visual features and high-level semantic visual concepts; 2) Integrated video access problem because of the lack of efficient video database indexing, automatic video annotation, and concept-oriented summary organization techniques. In this paper, we have proposed a novel framework, called ClassView, to make some advances toward more efficient video database indexing and access. 1) A hierarchical semantics-sensitive video classifier is proposed to shorten the semantic gap. The hierarchical tree structure of the semantics-sensitive video classifier is derived from the domain-dependent concept hierarchy of video contents in a database. Relevance analysis is used for selecting the discriminating visual features with suitable importances. The Expectation-Maximization (EM) algorithm is also used to determine the classification rule for each visual concept node in the classifier. 2) A hierarchical video database indexing and summary presentation technique is proposed to support more effective video access over a large-scale database. The hierarchical tree structure of our video database indexing scheme is determined by the domain-dependent concept hierarchy which is also used for video classification. The presentation of visual summary is also integrated with the inherent hierarchical video database indexing tree structure. Integrating video access with efficient database indexing tree structure has provided great opportunity for supporting more powerful video search engines.

KW - Video classification

KW - Video database indexing

KW - Video retrieval

KW - Visual summarization

UR - http://www.scopus.com/inward/record.url?scp=0742303682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0742303682&partnerID=8YFLogxK

U2 - 10.1109/TMM.2003.819583

DO - 10.1109/TMM.2003.819583

M3 - Article

VL - 6

SP - 70

EP - 86

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 1

ER -