A study of semantic context detection by using SVM and GMM approaches

Wei Ta Chu, Wen Huang Cheng, Ja Ling Wu, Jane Yung Jen Hsu

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

10 Citations (Scopus)

Abstract

Semantic-level content analysis is a crucial issue to achieve efficient content retrieval and management. In this paper, we propose a hierarchical approach that models the statistical characteristics of several audio events over a time series to accomplish semantic context detection. Two stages, including audio event and semantic context modeling/testing, are devised to bridge the semantic gap between physical audio features and semantic concepts. HMMs are used to model audio events, and SVMs and GMMs are used to fuse the characteristics of various audio events related to some specific semantic concepts. The experimental results show that the approach is effective in detecting semantic context. The comparison between SVM- and GMM-based approaches is also studied.

Original languageEnglish
Title of host publication2004 IEEE International Conference on Multimedia and Expo (ICME)
Pages1591-1594
Number of pages4
Publication statusPublished - 2004 Dec 1
Event2004 IEEE International Conference on Multimedia and Expo (ICME) - Taipei, Taiwan
Duration: 2004 Jun 272004 Jun 30

Publication series

Name2004 IEEE International Conference on Multimedia and Expo (ICME)
Volume3

Other

Other2004 IEEE International Conference on Multimedia and Expo (ICME)
CountryTaiwan
CityTaipei
Period04-06-2704-06-30

Fingerprint

Semantics
Electric fuses
Time series
Testing

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Chu, W. T., Cheng, W. H., Wu, J. L., & Hsu, J. Y. J. (2004). A study of semantic context detection by using SVM and GMM approaches. In 2004 IEEE International Conference on Multimedia and Expo (ICME) (pp. 1591-1594). (2004 IEEE International Conference on Multimedia and Expo (ICME); Vol. 3).
Chu, Wei Ta ; Cheng, Wen Huang ; Wu, Ja Ling ; Hsu, Jane Yung Jen. / A study of semantic context detection by using SVM and GMM approaches. 2004 IEEE International Conference on Multimedia and Expo (ICME). 2004. pp. 1591-1594 (2004 IEEE International Conference on Multimedia and Expo (ICME)).
@inproceedings{4bc05d0968174f52acb4a0b0dda503af,
title = "A study of semantic context detection by using SVM and GMM approaches",
abstract = "Semantic-level content analysis is a crucial issue to achieve efficient content retrieval and management. In this paper, we propose a hierarchical approach that models the statistical characteristics of several audio events over a time series to accomplish semantic context detection. Two stages, including audio event and semantic context modeling/testing, are devised to bridge the semantic gap between physical audio features and semantic concepts. HMMs are used to model audio events, and SVMs and GMMs are used to fuse the characteristics of various audio events related to some specific semantic concepts. The experimental results show that the approach is effective in detecting semantic context. The comparison between SVM- and GMM-based approaches is also studied.",
author = "Chu, {Wei Ta} and Cheng, {Wen Huang} and Wu, {Ja Ling} and Hsu, {Jane Yung Jen}",
year = "2004",
month = "12",
day = "1",
language = "English",
isbn = "0780386035",
series = "2004 IEEE International Conference on Multimedia and Expo (ICME)",
pages = "1591--1594",
booktitle = "2004 IEEE International Conference on Multimedia and Expo (ICME)",

}

Chu, WT, Cheng, WH, Wu, JL & Hsu, JYJ 2004, A study of semantic context detection by using SVM and GMM approaches. in 2004 IEEE International Conference on Multimedia and Expo (ICME). 2004 IEEE International Conference on Multimedia and Expo (ICME), vol. 3, pp. 1591-1594, 2004 IEEE International Conference on Multimedia and Expo (ICME), Taipei, Taiwan, 04-06-27.

A study of semantic context detection by using SVM and GMM approaches. / Chu, Wei Ta; Cheng, Wen Huang; Wu, Ja Ling; Hsu, Jane Yung Jen.

2004 IEEE International Conference on Multimedia and Expo (ICME). 2004. p. 1591-1594 (2004 IEEE International Conference on Multimedia and Expo (ICME); Vol. 3).

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

TY - GEN

T1 - A study of semantic context detection by using SVM and GMM approaches

AU - Chu, Wei Ta

AU - Cheng, Wen Huang

AU - Wu, Ja Ling

AU - Hsu, Jane Yung Jen

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Semantic-level content analysis is a crucial issue to achieve efficient content retrieval and management. In this paper, we propose a hierarchical approach that models the statistical characteristics of several audio events over a time series to accomplish semantic context detection. Two stages, including audio event and semantic context modeling/testing, are devised to bridge the semantic gap between physical audio features and semantic concepts. HMMs are used to model audio events, and SVMs and GMMs are used to fuse the characteristics of various audio events related to some specific semantic concepts. The experimental results show that the approach is effective in detecting semantic context. The comparison between SVM- and GMM-based approaches is also studied.

AB - Semantic-level content analysis is a crucial issue to achieve efficient content retrieval and management. In this paper, we propose a hierarchical approach that models the statistical characteristics of several audio events over a time series to accomplish semantic context detection. Two stages, including audio event and semantic context modeling/testing, are devised to bridge the semantic gap between physical audio features and semantic concepts. HMMs are used to model audio events, and SVMs and GMMs are used to fuse the characteristics of various audio events related to some specific semantic concepts. The experimental results show that the approach is effective in detecting semantic context. The comparison between SVM- and GMM-based approaches is also studied.

UR - http://www.scopus.com/inward/record.url?scp=11244352185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11244352185&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:11244352185

SN - 0780386035

SN - 9780780386037

T3 - 2004 IEEE International Conference on Multimedia and Expo (ICME)

SP - 1591

EP - 1594

BT - 2004 IEEE International Conference on Multimedia and Expo (ICME)

ER -

Chu WT, Cheng WH, Wu JL, Hsu JYJ. A study of semantic context detection by using SVM and GMM approaches. In 2004 IEEE International Conference on Multimedia and Expo (ICME). 2004. p. 1591-1594. (2004 IEEE International Conference on Multimedia and Expo (ICME)).