Multimedia classification

Shiyu Chang, Wei Han, Xianming Liu, Ning Xu, Pooya Khorrami, Thomas S. Huang

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Many machine classification problems resemble human decision making tasks, which are multimodal in nature. Humans have the capability to combine various types of sensory data and associate them with natural language entities. Complex decision tasks such as person identification often heavily depend on such synergy or fusion of different modalities. For that reason, much effort on machine classification methods goes into exploiting the underlying relationships among modalities and constructing an effective fusion algorithm. This is a fundamental step in the advancement of artificial intelligence, because the scope of learning algorithms is not limited to one type of sensory data.

Original languageEnglish (US)
Title of host publicationData Classification
Subtitle of host publicationAlgorithms and Applications
PublisherCRC Press
Pages337-364
Number of pages28
ISBN (Electronic)9781466586758
ISBN (Print)9781466586741
DOIs
StatePublished - Jan 1 2014

Fingerprint

Fusion reactions
Learning algorithms
Artificial intelligence
Decision making
Fusion
Multimedia
Learning algorithm
Language
Synergy

ASJC Scopus subject areas

  • Economics, Econometrics and Finance(all)
  • Business, Management and Accounting(all)
  • Computer Science(all)

Cite this

Chang, S., Han, W., Liu, X., Xu, N., Khorrami, P., & Huang, T. S. (2014). Multimedia classification. In Data Classification: Algorithms and Applications (pp. 337-364). CRC Press. https://doi.org/10.1201/b17320

Multimedia classification. / Chang, Shiyu; Han, Wei; Liu, Xianming; Xu, Ning; Khorrami, Pooya; Huang, Thomas S.

Data Classification: Algorithms and Applications. CRC Press, 2014. p. 337-364.

Research output: Chapter in Book/Report/Conference proceedingChapter

Chang, S, Han, W, Liu, X, Xu, N, Khorrami, P & Huang, TS 2014, Multimedia classification. in Data Classification: Algorithms and Applications. CRC Press, pp. 337-364. https://doi.org/10.1201/b17320
Chang S, Han W, Liu X, Xu N, Khorrami P, Huang TS. Multimedia classification. In Data Classification: Algorithms and Applications. CRC Press. 2014. p. 337-364 https://doi.org/10.1201/b17320
Chang, Shiyu ; Han, Wei ; Liu, Xianming ; Xu, Ning ; Khorrami, Pooya ; Huang, Thomas S. / Multimedia classification. Data Classification: Algorithms and Applications. CRC Press, 2014. pp. 337-364
@inbook{3eb371c7f13c4b2cbcf140e44eabcbbf,
title = "Multimedia classification",
abstract = "Many machine classification problems resemble human decision making tasks, which are multimodal in nature. Humans have the capability to combine various types of sensory data and associate them with natural language entities. Complex decision tasks such as person identification often heavily depend on such synergy or fusion of different modalities. For that reason, much effort on machine classification methods goes into exploiting the underlying relationships among modalities and constructing an effective fusion algorithm. This is a fundamental step in the advancement of artificial intelligence, because the scope of learning algorithms is not limited to one type of sensory data.",
author = "Shiyu Chang and Wei Han and Xianming Liu and Ning Xu and Pooya Khorrami and Huang, {Thomas S.}",
year = "2014",
month = "1",
day = "1",
doi = "10.1201/b17320",
language = "English (US)",
isbn = "9781466586741",
pages = "337--364",
booktitle = "Data Classification",
publisher = "CRC Press",

}

TY - CHAP

T1 - Multimedia classification

AU - Chang, Shiyu

AU - Han, Wei

AU - Liu, Xianming

AU - Xu, Ning

AU - Khorrami, Pooya

AU - Huang, Thomas S.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Many machine classification problems resemble human decision making tasks, which are multimodal in nature. Humans have the capability to combine various types of sensory data and associate them with natural language entities. Complex decision tasks such as person identification often heavily depend on such synergy or fusion of different modalities. For that reason, much effort on machine classification methods goes into exploiting the underlying relationships among modalities and constructing an effective fusion algorithm. This is a fundamental step in the advancement of artificial intelligence, because the scope of learning algorithms is not limited to one type of sensory data.

AB - Many machine classification problems resemble human decision making tasks, which are multimodal in nature. Humans have the capability to combine various types of sensory data and associate them with natural language entities. Complex decision tasks such as person identification often heavily depend on such synergy or fusion of different modalities. For that reason, much effort on machine classification methods goes into exploiting the underlying relationships among modalities and constructing an effective fusion algorithm. This is a fundamental step in the advancement of artificial intelligence, because the scope of learning algorithms is not limited to one type of sensory data.

UR - http://www.scopus.com/inward/record.url?scp=84970892988&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84970892988&partnerID=8YFLogxK

U2 - 10.1201/b17320

DO - 10.1201/b17320

M3 - Chapter

AN - SCOPUS:84970892988

SN - 9781466586741

SP - 337

EP - 364

BT - Data Classification

PB - CRC Press

ER -