BOUN-NKU in mediaeval 2017 emotional impact of movies task

Nihan Karslioglu; Yasemin Timar; Albert Ali Salah; Heysem Kaya

BOUN-NKU in mediaeval 2017 emotional impact of movies task

Nihan Karslioglu
, Yasemin Timar
, Albert Ali Salah
, Heysem Kaya

Boazii University

Research output: Working paper › Academic

Abstract

In this paper, we present our approach for the Emotional Impact of Movies task of Mediaeval 2017 Challenge, involving multimodal fusion for predicting arousal and valence for movie clips. In our system, we have two pipelines. In the first one, we extracted audio/visual features, and used a combination of PCA, Fisher vector encoding, feature selection, and extreme learning machine classifiers. In the second one, we focused on the classifiers, rather than on feature selection.

Original language	English
Publication status	Published - 12 Sept 2017

Publication series

Name	CEUR Workshop Proceedings
Publisher	CEUR WS
ISSN (Print)	1613-0073

Funding

This work is supported by Bogazici University Project BAP 16A01P4 and by the BAGEP Award of the Science Academy.

Cite this

@techreport{61593067b9034cf7a61723f27bb4ec9e,

title = "BOUN-NKU in mediaeval 2017 emotional impact of movies task",

abstract = "In this paper, we present our approach for the Emotional Impact of Movies task of Mediaeval 2017 Challenge, involving multimodal fusion for predicting arousal and valence for movie clips. In our system, we have two pipelines. In the first one, we extracted audio/visual features, and used a combination of PCA, Fisher vector encoding, feature selection, and extreme learning machine classifiers. In the second one, we focused on the classifiers, rather than on feature selection.",

author = "Nihan Karslioglu and Yasemin Timar and Salah, \{Albert Ali\} and Heysem Kaya",

year = "2017",

month = sep,

day = "12",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR WS",

type = "WorkingPaper",

institution = "CEUR WS",

}

TY - UNPB

T1 - BOUN-NKU in mediaeval 2017 emotional impact of movies task

AU - Karslioglu, Nihan

AU - Timar, Yasemin

AU - Salah, Albert Ali

AU - Kaya, Heysem

PY - 2017/9/12

Y1 - 2017/9/12

N2 - In this paper, we present our approach for the Emotional Impact of Movies task of Mediaeval 2017 Challenge, involving multimodal fusion for predicting arousal and valence for movie clips. In our system, we have two pipelines. In the first one, we extracted audio/visual features, and used a combination of PCA, Fisher vector encoding, feature selection, and extreme learning machine classifiers. In the second one, we focused on the classifiers, rather than on feature selection.

AB - In this paper, we present our approach for the Emotional Impact of Movies task of Mediaeval 2017 Challenge, involving multimodal fusion for predicting arousal and valence for movie clips. In our system, we have two pipelines. In the first one, we extracted audio/visual features, and used a combination of PCA, Fisher vector encoding, feature selection, and extreme learning machine classifiers. In the second one, we focused on the classifiers, rather than on feature selection.

UR - https://www.scopus.com/pages/publications/85034951892

M3 - Working paper

AN - SCOPUS:85034951892

T3 - CEUR Workshop Proceedings

BT - BOUN-NKU in mediaeval 2017 emotional impact of movies task

ER -

BOUN-NKU in mediaeval 2017 emotional impact of movies task

Abstract

Publication series

Funding

Other files and links

Fingerprint

Cite this