TUDCL at MediaEval 2013 Violent Scenes Detection: Training with multi-modal features by MKL

Shinichi Goto; Terumasa Aoki

TUDCL at MediaEval 2013 Violent Scenes Detection: Training with multi-modal features by MKL

Shinichi Goto, Terumasa Aoki

New Industry Creation Hatchery Center (NICHe)

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

The purpose of this paper is to describe the work carried out for the Violent Scenes Detection task at MediaEval 2013 by team TUDCL. Our work is based on the combination of visual, temporal and audio features with machine learning at segment-level. Block-saliency-map based dense trajectory is proposed for visual and temporal features, and MFCC and delta-MFCC is used for audio features. For the classification, Multiple Kernel Learning is applied, which is effective if multi-modal features exist.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	1043
Publication status	Published - 2013 Jan 1
Event	2013 Multimedia Benchmark Workshop, MediaEval 2013 - Barcelona, Spain Duration: 2013 Oct 18 → 2013 Oct 19

ASJC Scopus subject areas

Computer Science(all)

Fingerprint Dive into the research topics of 'TUDCL at MediaEval 2013 Violent Scenes Detection: Training with multi-modal features by MKL'. Together they form a unique fingerprint.

Cite this

@article{0176d33b94c94aac880c6f20ce309704,

title = "TUDCL at MediaEval 2013 Violent Scenes Detection: Training with multi-modal features by MKL",

abstract = "The purpose of this paper is to describe the work carried out for the Violent Scenes Detection task at MediaEval 2013 by team TUDCL. Our work is based on the combination of visual, temporal and audio features with machine learning at segment-level. Block-saliency-map based dense trajectory is proposed for visual and temporal features, and MFCC and delta-MFCC is used for audio features. For the classification, Multiple Kernel Learning is applied, which is effective if multi-modal features exist.",

author = "Shinichi Goto and Terumasa Aoki",

year = "2013",

month = jan,

day = "1",

language = "English",

volume = "1043",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

note = "2013 Multimedia Benchmark Workshop, MediaEval 2013 ; Conference date: 18-10-2013 Through 19-10-2013",

}

TY - JOUR

T1 - TUDCL at MediaEval 2013 Violent Scenes Detection

T2 - 2013 Multimedia Benchmark Workshop, MediaEval 2013

AU - Goto, Shinichi

AU - Aoki, Terumasa

PY - 2013/1/1

Y1 - 2013/1/1

N2 - The purpose of this paper is to describe the work carried out for the Violent Scenes Detection task at MediaEval 2013 by team TUDCL. Our work is based on the combination of visual, temporal and audio features with machine learning at segment-level. Block-saliency-map based dense trajectory is proposed for visual and temporal features, and MFCC and delta-MFCC is used for audio features. For the classification, Multiple Kernel Learning is applied, which is effective if multi-modal features exist.

AB - The purpose of this paper is to describe the work carried out for the Violent Scenes Detection task at MediaEval 2013 by team TUDCL. Our work is based on the combination of visual, temporal and audio features with machine learning at segment-level. Block-saliency-map based dense trajectory is proposed for visual and temporal features, and MFCC and delta-MFCC is used for audio features. For the classification, Multiple Kernel Learning is applied, which is effective if multi-modal features exist.

UR - http://www.scopus.com/inward/record.url?scp=84924769559&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924769559&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84924769559

VL - 1043

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

Y2 - 18 October 2013 through 19 October 2013

ER -

TUDCL at MediaEval 2013 Violent Scenes Detection: Training with multi-modal features by MKL

Abstract

ASJC Scopus subject areas

Other files and links

Cite this