Video event detection with combined distance-based and rule-based data mining techniques

Zongxing Xie, Mei-Ling Shyu, Shu Ching Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

In this paper, the rare event detection issue in video event detection is addressed through the proposed data mining framework which can be generalized to be domain independent. The fully automatic process via the combination of distance-based and rule-based data mining techniques can greatly reduce the number of negative (non-event) instances and the feature dimension to facilitate the final event detection, without pruning away any positive (event) testing instance along the process. The effectiveness and efficiency of the proposed framework are demonstrated over the goal event detection application based on a large collection of soccer videos with different styles.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
Pages2026-2029
Number of pages4
StatePublished - Dec 1 2007
EventIEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, China
Duration: Jul 2 2007Jul 5 2007

Other

OtherIEEE International Conference onMultimedia and Expo, ICME 2007
CountryChina
CityBeijing
Period7/2/077/5/07

Fingerprint

Data mining
Testing

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Xie, Z., Shyu, M-L., & Chen, S. C. (2007). Video event detection with combined distance-based and rule-based data mining techniques. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007 (pp. 2026-2029). [4285078]

Video event detection with combined distance-based and rule-based data mining techniques. / Xie, Zongxing; Shyu, Mei-Ling; Chen, Shu Ching.

Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. p. 2026-2029 4285078.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xie, Z, Shyu, M-L & Chen, SC 2007, Video event detection with combined distance-based and rule-based data mining techniques. in Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007., 4285078, pp. 2026-2029, IEEE International Conference onMultimedia and Expo, ICME 2007, Beijing, China, 7/2/07.
Xie Z, Shyu M-L, Chen SC. Video event detection with combined distance-based and rule-based data mining techniques. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. p. 2026-2029. 4285078
Xie, Zongxing ; Shyu, Mei-Ling ; Chen, Shu Ching. / Video event detection with combined distance-based and rule-based data mining techniques. Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. pp. 2026-2029
@inproceedings{8ec6a6e285414a118ff46395c8f57409,
title = "Video event detection with combined distance-based and rule-based data mining techniques",
abstract = "In this paper, the rare event detection issue in video event detection is addressed through the proposed data mining framework which can be generalized to be domain independent. The fully automatic process via the combination of distance-based and rule-based data mining techniques can greatly reduce the number of negative (non-event) instances and the feature dimension to facilitate the final event detection, without pruning away any positive (event) testing instance along the process. The effectiveness and efficiency of the proposed framework are demonstrated over the goal event detection application based on a large collection of soccer videos with different styles.",
author = "Zongxing Xie and Mei-Ling Shyu and Chen, {Shu Ching}",
year = "2007",
month = "12",
day = "1",
language = "English",
isbn = "1424410177",
pages = "2026--2029",
booktitle = "Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007",

}

TY - GEN

T1 - Video event detection with combined distance-based and rule-based data mining techniques

AU - Xie, Zongxing

AU - Shyu, Mei-Ling

AU - Chen, Shu Ching

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, the rare event detection issue in video event detection is addressed through the proposed data mining framework which can be generalized to be domain independent. The fully automatic process via the combination of distance-based and rule-based data mining techniques can greatly reduce the number of negative (non-event) instances and the feature dimension to facilitate the final event detection, without pruning away any positive (event) testing instance along the process. The effectiveness and efficiency of the proposed framework are demonstrated over the goal event detection application based on a large collection of soccer videos with different styles.

AB - In this paper, the rare event detection issue in video event detection is addressed through the proposed data mining framework which can be generalized to be domain independent. The fully automatic process via the combination of distance-based and rule-based data mining techniques can greatly reduce the number of negative (non-event) instances and the feature dimension to facilitate the final event detection, without pruning away any positive (event) testing instance along the process. The effectiveness and efficiency of the proposed framework are demonstrated over the goal event detection application based on a large collection of soccer videos with different styles.

UR - http://www.scopus.com/inward/record.url?scp=46449127794&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46449127794&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:46449127794

SN - 1424410177

SN - 9781424410170

SP - 2026

EP - 2029

BT - Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

ER -