Audio-visual event detection using duration dependent input output Markov models

M. R. Naphade; A. Garg; T. S. Huang

doi:10.1109/IVL.2001.990854

Audio-visual event detection using duration dependent input output Markov models

M. R. Naphade, A. Garg, T. S. Huang

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

Abstract

Analysis of audio-visual data and detection of semantic events with spatio-temporal support is a challenging multimedia understanding problem. The difficulty lies in the gap that exists between low level media features and high level semantic concept. We introduce a duration dependent input output Markov model (DDIOMM) to detect events based on multiple modalities. The DDIOMM combines the ability to model non-exponential duration densities with the mapping of input sequences to output sequences. We test the DDIOMM by modelling the audio-visual event explosion. We compare the detection performance of the DDIOMM with the IOMM as well as the HMM. Experiments reveal that modeling of duration improves detection performance.

Original language	English (US)
Title of host publication	Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	39-43
Number of pages	5
ISBN (Electronic)	0769513549, 9780769513546
DOIs	https://doi.org/10.1109/IVL.2001.990854
State	Published - 2001
Externally published	Yes
Event	IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001 - Kauai, United States Duration: Dec 14 2001 → …

Publication series

Name	Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001

Other

Other	IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001
Country/Territory	United States
City	Kauai
Period	12/14/01 → …

ASJC Scopus subject areas

General Computer Science

Online availability

10.1109/IVL.2001.990854

Library availability

Discover UIUC Full Text

Cite this

Naphade, M. R., Garg, A., & Huang, T. S. (2001). Audio-visual event detection using duration dependent input output Markov models. In Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001 (pp. 39-43). Article 990854 (Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IVL.2001.990854

Audio-visual event detection using duration dependent input output Markov models. / Naphade, M. R.; Garg, A.; Huang, T. S.
Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001. Institute of Electrical and Electronics Engineers Inc., 2001. p. 39-43 990854 (Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001).

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

Naphade, MR, Garg, A & Huang, TS 2001, Audio-visual event detection using duration dependent input output Markov models. in Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001., 990854, Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001, Institute of Electrical and Electronics Engineers Inc., pp. 39-43, IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001, Kauai, United States, 12/14/01. https://doi.org/10.1109/IVL.2001.990854

Naphade MR, Garg A, Huang TS. Audio-visual event detection using duration dependent input output Markov models. In Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001. Institute of Electrical and Electronics Engineers Inc. 2001. p. 39-43. 990854. (Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001). doi: 10.1109/IVL.2001.990854

Naphade, M. R. ; Garg, A. ; Huang, T. S. / Audio-visual event detection using duration dependent input output Markov models. Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001. Institute of Electrical and Electronics Engineers Inc., 2001. pp. 39-43 (Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001).

@inproceedings{2214e20a25d44e5e9dfb4295a5aefd17,

title = "Audio-visual event detection using duration dependent input output Markov models",

abstract = "Analysis of audio-visual data and detection of semantic events with spatio-temporal support is a challenging multimedia understanding problem. The difficulty lies in the gap that exists between low level media features and high level semantic concept. We introduce a duration dependent input output Markov model (DDIOMM) to detect events based on multiple modalities. The DDIOMM combines the ability to model non-exponential duration densities with the mapping of input sequences to output sequences. We test the DDIOMM by modelling the audio-visual event explosion. We compare the detection performance of the DDIOMM with the IOMM as well as the HMM. Experiments reveal that modeling of duration improves detection performance.",

author = "Naphade, {M. R.} and A. Garg and Huang, {T. S.}",

note = "Publisher Copyright: {\textcopyright} 2001 IEEE.; IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001 ; Conference date: 14-12-2001",

year = "2001",

doi = "10.1109/IVL.2001.990854",

language = "English (US)",

series = "Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "39--43",

booktitle = "Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001",

address = "United States",

}

TY - GEN

T1 - Audio-visual event detection using duration dependent input output Markov models

AU - Naphade, M. R.

AU - Garg, A.

AU - Huang, T. S.

PY - 2001

Y1 - 2001

N2 - Analysis of audio-visual data and detection of semantic events with spatio-temporal support is a challenging multimedia understanding problem. The difficulty lies in the gap that exists between low level media features and high level semantic concept. We introduce a duration dependent input output Markov model (DDIOMM) to detect events based on multiple modalities. The DDIOMM combines the ability to model non-exponential duration densities with the mapping of input sequences to output sequences. We test the DDIOMM by modelling the audio-visual event explosion. We compare the detection performance of the DDIOMM with the IOMM as well as the HMM. Experiments reveal that modeling of duration improves detection performance.

AB - Analysis of audio-visual data and detection of semantic events with spatio-temporal support is a challenging multimedia understanding problem. The difficulty lies in the gap that exists between low level media features and high level semantic concept. We introduce a duration dependent input output Markov model (DDIOMM) to detect events based on multiple modalities. The DDIOMM combines the ability to model non-exponential duration densities with the mapping of input sequences to output sequences. We test the DDIOMM by modelling the audio-visual event explosion. We compare the detection performance of the DDIOMM with the IOMM as well as the HMM. Experiments reveal that modeling of duration improves detection performance.

UR - http://www.scopus.com/inward/record.url?scp=33645155188&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645155188&partnerID=8YFLogxK

U2 - 10.1109/IVL.2001.990854

DO - 10.1109/IVL.2001.990854

M3 - Conference contribution

AN - SCOPUS:33645155188

T3 - Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001

SP - 39

EP - 43

BT - Proceedings - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE Workshop on Content-Based Access of Image and Video Libraries, CBAIVL 2001

Y2 - 14 December 2001

ER -

Audio-visual event detection using duration dependent input output Markov models

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this