A subspace symbolization approach to content-based video search

Xiangmin Zhou; Xiaofang Zhou; Athman Bouguettaya; John A. Taylor

doi:10.1109/ICDE.2009.198

A subspace symbolization approach to content-based video search

Xiangmin Zhou^*, Xiaofang Zhou^*, Athman Bouguettaya, John A. Taylor

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

We propose a subspace symbolization approach, namely SUDS, for content-based search on very large video databases. The novelty of SUDS is that it explores the data distribution in subspaces to build a visual dictionary. With this dictionary, the video data are processed using string matching techniques with two-step data simplification. A compact video representation model is developed by transforming each keyframe into a word that is a series of symbols in the dominant subspaces. Then, we present an innovative similarity measure called ED, which draws from the concept of the edit distance on strings to conduct video matching. The experimental results demonstrate the high effectiveness of SUDS with optimal parameters.

Original language	English
Title of host publication	Proceedings - 25th IEEE International Conference on Data Engineering, ICDE 2009
Pages	1191-1194
Number of pages	4
DOIs	https://doi.org/10.1109/ICDE.2009.198
Publication status	Published - 2009
Externally published	Yes
Event	25th IEEE International Conference on Data Engineering, ICDE 2009 - Shanghai, China Duration: 29 Mar 2009 → 2 Apr 2009

Publication series

Name	Proceedings - International Conference on Data Engineering
ISSN (Print)	1084-4627

Conference

Conference	25th IEEE International Conference on Data Engineering, ICDE 2009
Country/Territory	China
City	Shanghai
Period	29/03/09 → 2/04/09

Access to Document

10.1109/ICDE.2009.198

Cite this

@inproceedings{cc12d8d8f4694099bc82af8d773a2f2f,

title = "A subspace symbolization approach to content-based video search",

abstract = "We propose a subspace symbolization approach, namely SUDS, for content-based search on very large video databases. The novelty of SUDS is that it explores the data distribution in subspaces to build a visual dictionary. With this dictionary, the video data are processed using string matching techniques with two-step data simplification. A compact video representation model is developed by transforming each keyframe into a word that is a series of symbols in the dominant subspaces. Then, we present an innovative similarity measure called ED, which draws from the concept of the edit distance on strings to conduct video matching. The experimental results demonstrate the high effectiveness of SUDS with optimal parameters.",

author = "Xiangmin Zhou and Xiaofang Zhou and Athman Bouguettaya and Taylor, {John A.}",

year = "2009",

doi = "10.1109/ICDE.2009.198",

language = "English",

isbn = "9780769535456",

series = "Proceedings - International Conference on Data Engineering",

pages = "1191--1194",

booktitle = "Proceedings - 25th IEEE International Conference on Data Engineering, ICDE 2009",

note = "25th IEEE International Conference on Data Engineering, ICDE 2009 ; Conference date: 29-03-2009 Through 02-04-2009",

}

Zhou, X, Zhou, X, Bouguettaya, A & Taylor, JA 2009, A subspace symbolization approach to content-based video search. in Proceedings - 25th IEEE International Conference on Data Engineering, ICDE 2009., 4812498, Proceedings - International Conference on Data Engineering, pp. 1191-1194, 25th IEEE International Conference on Data Engineering, ICDE 2009, Shanghai, China, 29/03/09. https://doi.org/10.1109/ICDE.2009.198

A subspace symbolization approach to content-based video search. / Zhou, Xiangmin; Zhou, Xiaofang; Bouguettaya, Athman et al.
Proceedings - 25th IEEE International Conference on Data Engineering, ICDE 2009. 2009. p. 1191-1194 4812498 (Proceedings - International Conference on Data Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A subspace symbolization approach to content-based video search

AU - Zhou, Xiangmin

AU - Zhou, Xiaofang

AU - Bouguettaya, Athman

AU - Taylor, John A.

PY - 2009

Y1 - 2009

N2 - We propose a subspace symbolization approach, namely SUDS, for content-based search on very large video databases. The novelty of SUDS is that it explores the data distribution in subspaces to build a visual dictionary. With this dictionary, the video data are processed using string matching techniques with two-step data simplification. A compact video representation model is developed by transforming each keyframe into a word that is a series of symbols in the dominant subspaces. Then, we present an innovative similarity measure called ED, which draws from the concept of the edit distance on strings to conduct video matching. The experimental results demonstrate the high effectiveness of SUDS with optimal parameters.

AB - We propose a subspace symbolization approach, namely SUDS, for content-based search on very large video databases. The novelty of SUDS is that it explores the data distribution in subspaces to build a visual dictionary. With this dictionary, the video data are processed using string matching techniques with two-step data simplification. A compact video representation model is developed by transforming each keyframe into a word that is a series of symbols in the dominant subspaces. Then, we present an innovative similarity measure called ED, which draws from the concept of the edit distance on strings to conduct video matching. The experimental results demonstrate the high effectiveness of SUDS with optimal parameters.

UR - http://www.scopus.com/inward/record.url?scp=67649647579&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2009.198

DO - 10.1109/ICDE.2009.198

M3 - Conference contribution

SN - 9780769535456

T3 - Proceedings - International Conference on Data Engineering

SP - 1191

EP - 1194

BT - Proceedings - 25th IEEE International Conference on Data Engineering, ICDE 2009

T2 - 25th IEEE International Conference on Data Engineering, ICDE 2009

Y2 - 29 March 2009 through 2 April 2009

ER -

A subspace symbolization approach to content-based video search

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this