Feature Extraction for Multimedia Analysis

Rachid Benmokhtar; Benoit Huet; Gaël Richard; Slim Essid

doi:10.1002/9781119970231.ch4

Feature Extraction for Multimedia Analysis

Rachid Benmokhtar
, Benoit Huet
, Gaël Richard
, Slim Essid

Eurecom

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Original language	English
Title of host publication	Multimedia Semantics
Subtitle of host publication	Metadata, Analysis and Interaction
Publisher	John Wiley and Sons
Pages	35-58
Number of pages	24
ISBN (Print)	9780470747001
DOIs	https://doi.org/10.1002/9781119970231.ch4
Publication status	Published - 8 Aug 2011

Keywords

Cepstral features, in speech recognition - and speaker recognition
Feature extraction - for multimedia analysis
Feature extraction, step - for processing of multimedia content semantics
Feature fusion and multi-modality - features extracted from different modalities
Low-level feature extraction - MPEG-7, structures of, descriptor aggregation or localization
Motion descriptions in video sequences - powerful clues, as to content
Moving Picture Experts Group (MPEG) consortium - standardizing multimedia content description
Plethora of low-level features, available - multi-feature and multi-modal fusion
Visual descriptor properties - color descriptors, bins for fast indexing and fast queries
Visual modality, and video shot segmentation - human body, object recognition and motion analysis

Access to Document

10.1002/9781119970231.ch4

Cite this

@inbook{8fc4fc2b517e4e69ae0635aae56de8c6,

title = "Feature Extraction for Multimedia Analysis",

keywords = "Cepstral features, in speech recognition - and speaker recognition, Feature extraction - for multimedia analysis, Feature extraction, step - for processing of multimedia content semantics, Feature fusion and multi-modality - features extracted from different modalities, Low-level feature extraction - MPEG-7, structures of, descriptor aggregation or localization, Motion descriptions in video sequences - powerful clues, as to content, Moving Picture Experts Group (MPEG) consortium - standardizing multimedia content description, Plethora of low-level features, available - multi-feature and multi-modal fusion, Visual descriptor properties - color descriptors, bins for fast indexing and fast queries, Visual modality, and video shot segmentation - human body, object recognition and motion analysis",

author = "Rachid Benmokhtar and Benoit Huet and Ga{\"e}l Richard and Slim Essid",

year = "2011",

month = aug,

day = "8",

doi = "10.1002/9781119970231.ch4",

language = "English",

isbn = "9780470747001",

pages = "35--58",

booktitle = "Multimedia Semantics",

publisher = "John Wiley and Sons",

}

TY - CHAP

T1 - Feature Extraction for Multimedia Analysis

AU - Benmokhtar, Rachid

AU - Huet, Benoit

AU - Richard, Gaël

AU - Essid, Slim

PY - 2011/8/8

Y1 - 2011/8/8

KW - Cepstral features, in speech recognition - and speaker recognition

KW - Feature extraction - for multimedia analysis

KW - Feature extraction, step - for processing of multimedia content semantics

KW - Feature fusion and multi-modality - features extracted from different modalities

KW - Low-level feature extraction - MPEG-7, structures of, descriptor aggregation or localization

KW - Motion descriptions in video sequences - powerful clues, as to content

KW - Moving Picture Experts Group (MPEG) consortium - standardizing multimedia content description

KW - Plethora of low-level features, available - multi-feature and multi-modal fusion

KW - Visual descriptor properties - color descriptors, bins for fast indexing and fast queries

KW - Visual modality, and video shot segmentation - human body, object recognition and motion analysis

U2 - 10.1002/9781119970231.ch4

DO - 10.1002/9781119970231.ch4

M3 - Chapter

AN - SCOPUS:84886216074

SN - 9780470747001

SP - 35

EP - 58

BT - Multimedia Semantics

PB - John Wiley and Sons

ER -