KU-ISPL TRECVID 2014 multimedia event detection system

Seongjae Lee; Han Wang; Minseok Keum; Dubok Park; Hyunsik Choi; Zaur Fataliyev; Hanseok Ko

KU-ISPL TRECVID 2014 multimedia event detection system

Seongjae Lee, Han Wang, Minseok Keum, Dubok Park, Hyunsik Choi, Zaur Fataliyev, Hanseok Ko

School of Electrical Engineering

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

In this paper, KU-ISPL's system for TRECVID 2014 Multimedia Event Detection (MED) task is described. The system essentially combines various attributes for scene analysis; audio information for Acoustic Scene Analysis (ASA), Automatic Speech Recognition (ASR), visual information for Visual Scene Analysis (VSA), and Optical Character Recognition (OCR). In the fusion process, heterogeneous data from each module is incorporated, and then the rank of event for each video can be generated according to the final score. In order to verify the effectiveness of our system, we have participated with the following tasks of MED; Pre-specified 010EX, Pre-specified 100EX, Ad-hoc 010EX, and Ad-hoc 100EX. The result of our first participation from NIST shows that the Mean Average Precision (MAP) scores of each MED task were 2.3%, 4.6%, 2.1%, and 2.7%, respectively.

Original language	English
Publication status	Published - 2020
Event	2014 TREC Video Retrieval Evaluation, TRECVID 2014 - Orlando, United States Duration: 2014 Nov 10 → 2014 Nov 12

Conference

Conference	2014 TREC Video Retrieval Evaluation, TRECVID 2014
Country/Territory	United States
City	Orlando
Period	14/11/10 → 14/11/12

Bibliographical note

Publisher Copyright:
© 2020 2014 TREC Video Retrieval Evaluation. All rights reserved.

ASJC Scopus subject areas

Information Systems
Signal Processing
Electrical and Electronic Engineering

Cite this

@conference{4c01d993e0594c4391060412ac352155,

title = "KU-ISPL TRECVID 2014 multimedia event detection system",

abstract = "In this paper, KU-ISPL's system for TRECVID 2014 Multimedia Event Detection (MED) task is described. The system essentially combines various attributes for scene analysis; audio information for Acoustic Scene Analysis (ASA), Automatic Speech Recognition (ASR), visual information for Visual Scene Analysis (VSA), and Optical Character Recognition (OCR). In the fusion process, heterogeneous data from each module is incorporated, and then the rank of event for each video can be generated according to the final score. In order to verify the effectiveness of our system, we have participated with the following tasks of MED; Pre-specified 010EX, Pre-specified 100EX, Ad-hoc 010EX, and Ad-hoc 100EX. The result of our first participation from NIST shows that the Mean Average Precision (MAP) scores of each MED task were 2.3%, 4.6%, 2.1%, and 2.7%, respectively.",

author = "Seongjae Lee and Han Wang and Minseok Keum and Dubok Park and Hyunsik Choi and Zaur Fataliyev and Hanseok Ko",

note = "Publisher Copyright: {\textcopyright} 2020 2014 TREC Video Retrieval Evaluation. All rights reserved.; 2014 TREC Video Retrieval Evaluation, TRECVID 2014 ; Conference date: 10-11-2014 Through 12-11-2014",

year = "2020",

language = "English",

}

TY - CONF

T1 - KU-ISPL TRECVID 2014 multimedia event detection system

AU - Lee, Seongjae

AU - Wang, Han

AU - Keum, Minseok

AU - Park, Dubok

AU - Choi, Hyunsik

AU - Fataliyev, Zaur

AU - Ko, Hanseok

PY - 2020

Y1 - 2020

N2 - In this paper, KU-ISPL's system for TRECVID 2014 Multimedia Event Detection (MED) task is described. The system essentially combines various attributes for scene analysis; audio information for Acoustic Scene Analysis (ASA), Automatic Speech Recognition (ASR), visual information for Visual Scene Analysis (VSA), and Optical Character Recognition (OCR). In the fusion process, heterogeneous data from each module is incorporated, and then the rank of event for each video can be generated according to the final score. In order to verify the effectiveness of our system, we have participated with the following tasks of MED; Pre-specified 010EX, Pre-specified 100EX, Ad-hoc 010EX, and Ad-hoc 100EX. The result of our first participation from NIST shows that the Mean Average Precision (MAP) scores of each MED task were 2.3%, 4.6%, 2.1%, and 2.7%, respectively.

AB - In this paper, KU-ISPL's system for TRECVID 2014 Multimedia Event Detection (MED) task is described. The system essentially combines various attributes for scene analysis; audio information for Acoustic Scene Analysis (ASA), Automatic Speech Recognition (ASR), visual information for Visual Scene Analysis (VSA), and Optical Character Recognition (OCR). In the fusion process, heterogeneous data from each module is incorporated, and then the rank of event for each video can be generated according to the final score. In order to verify the effectiveness of our system, we have participated with the following tasks of MED; Pre-specified 010EX, Pre-specified 100EX, Ad-hoc 010EX, and Ad-hoc 100EX. The result of our first participation from NIST shows that the Mean Average Precision (MAP) scores of each MED task were 2.3%, 4.6%, 2.1%, and 2.7%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85085052599&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85085052599

T2 - 2014 TREC Video Retrieval Evaluation, TRECVID 2014

Y2 - 10 November 2014 through 12 November 2014

ER -

KU-ISPL TRECVID 2014 multimedia event detection system

Abstract

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this