Neural network based framework for goal event detection in soccer videos

Kasun Wickramaratna, Min Chen, Shu Ching Chen, Mei-Ling Shyu

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

12 Citations (Scopus)

Abstract

In this paper, a neural network based framework for semantic event detection in soccer videos is proposed. The framework provides a robust solution for soccer goal event detection by combining the strength of multimodal analysis and the ability of neural network ensembles to reduce the generalization error. Due to the rareness of the goal events, the bootstrapped sampling method on the training set is utilized to enhance the recall of goal event detection. Then a group of component networks are trained using all the available training data. The precision of the detection is greatly improved via the following two steps. First, a pre-filtering step is employed on the test set to reduce the noisy and inconsistent data, and then an advanced weighting scheme is proposed to intelligently traverse and combine the component network predictions by taking into consideration the prediction performance of each network. A set of experiments are designed to compare the performance of different bootstrapped sampling schemes, to present the strength of the proposed weighting scheme in event detection, and to demonstrate the effectiveness of our framework for soccer goal event detection.

Original languageEnglish
Title of host publicationProceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005
Pages21-28
Number of pages8
Volume2005
DOIs
StatePublished - Dec 1 2005
EventSeventh IEEE International Symposium on Multimedia, ISM 2005 - Irvine, CA, United States
Duration: Dec 12 2005Dec 14 2005

Other

OtherSeventh IEEE International Symposium on Multimedia, ISM 2005
CountryUnited States
CityIrvine, CA
Period12/12/0512/14/05

Fingerprint

Network components
Sampling
Neural networks
Semantics
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Wickramaratna, K., Chen, M., Chen, S. C., & Shyu, M-L. (2005). Neural network based framework for goal event detection in soccer videos. In Proceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005 (Vol. 2005, pp. 21-28). [1565809] https://doi.org/10.1109/ISM.2005.83

Neural network based framework for goal event detection in soccer videos. / Wickramaratna, Kasun; Chen, Min; Chen, Shu Ching; Shyu, Mei-Ling.

Proceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005. Vol. 2005 2005. p. 21-28 1565809.

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

Wickramaratna, K, Chen, M, Chen, SC & Shyu, M-L 2005, Neural network based framework for goal event detection in soccer videos. in Proceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005. vol. 2005, 1565809, pp. 21-28, Seventh IEEE International Symposium on Multimedia, ISM 2005, Irvine, CA, United States, 12/12/05. https://doi.org/10.1109/ISM.2005.83
Wickramaratna K, Chen M, Chen SC, Shyu M-L. Neural network based framework for goal event detection in soccer videos. In Proceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005. Vol. 2005. 2005. p. 21-28. 1565809 https://doi.org/10.1109/ISM.2005.83
Wickramaratna, Kasun ; Chen, Min ; Chen, Shu Ching ; Shyu, Mei-Ling. / Neural network based framework for goal event detection in soccer videos. Proceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005. Vol. 2005 2005. pp. 21-28
@inproceedings{ce88534594284417a3db1638cac3ef90,
title = "Neural network based framework for goal event detection in soccer videos",
abstract = "In this paper, a neural network based framework for semantic event detection in soccer videos is proposed. The framework provides a robust solution for soccer goal event detection by combining the strength of multimodal analysis and the ability of neural network ensembles to reduce the generalization error. Due to the rareness of the goal events, the bootstrapped sampling method on the training set is utilized to enhance the recall of goal event detection. Then a group of component networks are trained using all the available training data. The precision of the detection is greatly improved via the following two steps. First, a pre-filtering step is employed on the test set to reduce the noisy and inconsistent data, and then an advanced weighting scheme is proposed to intelligently traverse and combine the component network predictions by taking into consideration the prediction performance of each network. A set of experiments are designed to compare the performance of different bootstrapped sampling schemes, to present the strength of the proposed weighting scheme in event detection, and to demonstrate the effectiveness of our framework for soccer goal event detection.",
author = "Kasun Wickramaratna and Min Chen and Chen, {Shu Ching} and Mei-Ling Shyu",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/ISM.2005.83",
language = "English",
isbn = "0769524893",
volume = "2005",
pages = "21--28",
booktitle = "Proceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005",

}

TY - GEN

T1 - Neural network based framework for goal event detection in soccer videos

AU - Wickramaratna, Kasun

AU - Chen, Min

AU - Chen, Shu Ching

AU - Shyu, Mei-Ling

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this paper, a neural network based framework for semantic event detection in soccer videos is proposed. The framework provides a robust solution for soccer goal event detection by combining the strength of multimodal analysis and the ability of neural network ensembles to reduce the generalization error. Due to the rareness of the goal events, the bootstrapped sampling method on the training set is utilized to enhance the recall of goal event detection. Then a group of component networks are trained using all the available training data. The precision of the detection is greatly improved via the following two steps. First, a pre-filtering step is employed on the test set to reduce the noisy and inconsistent data, and then an advanced weighting scheme is proposed to intelligently traverse and combine the component network predictions by taking into consideration the prediction performance of each network. A set of experiments are designed to compare the performance of different bootstrapped sampling schemes, to present the strength of the proposed weighting scheme in event detection, and to demonstrate the effectiveness of our framework for soccer goal event detection.

AB - In this paper, a neural network based framework for semantic event detection in soccer videos is proposed. The framework provides a robust solution for soccer goal event detection by combining the strength of multimodal analysis and the ability of neural network ensembles to reduce the generalization error. Due to the rareness of the goal events, the bootstrapped sampling method on the training set is utilized to enhance the recall of goal event detection. Then a group of component networks are trained using all the available training data. The precision of the detection is greatly improved via the following two steps. First, a pre-filtering step is employed on the test set to reduce the noisy and inconsistent data, and then an advanced weighting scheme is proposed to intelligently traverse and combine the component network predictions by taking into consideration the prediction performance of each network. A set of experiments are designed to compare the performance of different bootstrapped sampling schemes, to present the strength of the proposed weighting scheme in event detection, and to demonstrate the effectiveness of our framework for soccer goal event detection.

UR - http://www.scopus.com/inward/record.url?scp=33846304687&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846304687&partnerID=8YFLogxK

U2 - 10.1109/ISM.2005.83

DO - 10.1109/ISM.2005.83

M3 - Conference contribution

SN - 0769524893

SN - 9780769524894

VL - 2005

SP - 21

EP - 28

BT - Proceedings - Seventh IEEE International Symposium on Multimedia, ISM 2005

ER -