Discriminative learning- assisted video semantic concept classification

Qiusha Zhu, Mei-Ling Shyu, Shu Ching Chen

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

With the fast development and wide usage of digital devices, more and more people like to record their daily lives as videos and share them on websites such as YouTube, Yahoo Video, and Youku, to name a few. To get a better understanding of such video data and discover useful knowledge from them, effective and automatic multimedia semantic analysis becomes crucial. However, a manual analysis of multimedia data can be very expensive or simply not feasible when the time is limited or when the amount of data is enormous. Hence, the multimedia research community faces a major challenge: how to effectively and efficiently organize these videos. Data mining techniques have been successfully utilized to provide solutions to such a challenge. An example is video concept classification, which has been an attractive research focus in the past 10 years (Chen et al., 2006a; Shyu et al., 2008).

Original languageEnglish (US)
Title of host publicationMultimedia Security
Subtitle of host publicationWatermarking, Steganography, and Forensics
PublisherCRC Press
Pages31-49
Number of pages19
ISBN (Electronic)9781439873328
ISBN (Print)9781439873311
DOIs
StatePublished - Jan 1 2017

Fingerprint

Semantics
Digital devices
Data mining
Websites

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Cite this

Zhu, Q., Shyu, M-L., & Chen, S. C. (2017). Discriminative learning- assisted video semantic concept classification. In Multimedia Security: Watermarking, Steganography, and Forensics (pp. 31-49). CRC Press. https://doi.org/10.1201/b12697

Discriminative learning- assisted video semantic concept classification. / Zhu, Qiusha; Shyu, Mei-Ling; Chen, Shu Ching.

Multimedia Security: Watermarking, Steganography, and Forensics. CRC Press, 2017. p. 31-49.

Research output: Chapter in Book/Report/Conference proceedingChapter

Zhu, Q, Shyu, M-L & Chen, SC 2017, Discriminative learning- assisted video semantic concept classification. in Multimedia Security: Watermarking, Steganography, and Forensics. CRC Press, pp. 31-49. https://doi.org/10.1201/b12697
Zhu Q, Shyu M-L, Chen SC. Discriminative learning- assisted video semantic concept classification. In Multimedia Security: Watermarking, Steganography, and Forensics. CRC Press. 2017. p. 31-49 https://doi.org/10.1201/b12697
Zhu, Qiusha ; Shyu, Mei-Ling ; Chen, Shu Ching. / Discriminative learning- assisted video semantic concept classification. Multimedia Security: Watermarking, Steganography, and Forensics. CRC Press, 2017. pp. 31-49
@inbook{ef0bd3225db541589e2618579937a8e9,
title = "Discriminative learning- assisted video semantic concept classification",
abstract = "With the fast development and wide usage of digital devices, more and more people like to record their daily lives as videos and share them on websites such as YouTube, Yahoo Video, and Youku, to name a few. To get a better understanding of such video data and discover useful knowledge from them, effective and automatic multimedia semantic analysis becomes crucial. However, a manual analysis of multimedia data can be very expensive or simply not feasible when the time is limited or when the amount of data is enormous. Hence, the multimedia research community faces a major challenge: how to effectively and efficiently organize these videos. Data mining techniques have been successfully utilized to provide solutions to such a challenge. An example is video concept classification, which has been an attractive research focus in the past 10 years (Chen et al., 2006a; Shyu et al., 2008).",
author = "Qiusha Zhu and Mei-Ling Shyu and Chen, {Shu Ching}",
year = "2017",
month = "1",
day = "1",
doi = "10.1201/b12697",
language = "English (US)",
isbn = "9781439873311",
pages = "31--49",
booktitle = "Multimedia Security",
publisher = "CRC Press",

}

TY - CHAP

T1 - Discriminative learning- assisted video semantic concept classification

AU - Zhu, Qiusha

AU - Shyu, Mei-Ling

AU - Chen, Shu Ching

PY - 2017/1/1

Y1 - 2017/1/1

N2 - With the fast development and wide usage of digital devices, more and more people like to record their daily lives as videos and share them on websites such as YouTube, Yahoo Video, and Youku, to name a few. To get a better understanding of such video data and discover useful knowledge from them, effective and automatic multimedia semantic analysis becomes crucial. However, a manual analysis of multimedia data can be very expensive or simply not feasible when the time is limited or when the amount of data is enormous. Hence, the multimedia research community faces a major challenge: how to effectively and efficiently organize these videos. Data mining techniques have been successfully utilized to provide solutions to such a challenge. An example is video concept classification, which has been an attractive research focus in the past 10 years (Chen et al., 2006a; Shyu et al., 2008).

AB - With the fast development and wide usage of digital devices, more and more people like to record their daily lives as videos and share them on websites such as YouTube, Yahoo Video, and Youku, to name a few. To get a better understanding of such video data and discover useful knowledge from them, effective and automatic multimedia semantic analysis becomes crucial. However, a manual analysis of multimedia data can be very expensive or simply not feasible when the time is limited or when the amount of data is enormous. Hence, the multimedia research community faces a major challenge: how to effectively and efficiently organize these videos. Data mining techniques have been successfully utilized to provide solutions to such a challenge. An example is video concept classification, which has been an attractive research focus in the past 10 years (Chen et al., 2006a; Shyu et al., 2008).

UR - http://www.scopus.com/inward/record.url?scp=85027717230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027717230&partnerID=8YFLogxK

U2 - 10.1201/b12697

DO - 10.1201/b12697

M3 - Chapter

SN - 9781439873311

SP - 31

EP - 49

BT - Multimedia Security

PB - CRC Press

ER -