@inproceedings{shafaei-etal-2021-case,
title = "A Case Study of Deep Learning-Based Multi-Modal Methods for Labeling the Presence of Questionable Content in Movie Trailers",
author = "Shafaei, Mahsa and
Smailis, Christos and
Kakadiaris, Ioannis and
Solorio, Thamar",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.146/",
pages = "1297--1307",
abstract = "In this work, we explore different approaches to combine modalities for the problem of automated age-suitability rating of movie trailers. First, we introduce a new dataset containing videos of movie trailers in English downloaded from IMDB and YouTube, along with their corresponding age-suitability rating labels. Secondly, we propose a multi-modal deep learning pipeline addressing the movie trailer age suitability rating problem. This is the first attempt to combine video, audio, and speech information for this problem, and our experimental results show that multi-modal approaches significantly outperform the best mono and bimodal models in this task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shafaei-etal-2021-case">
<titleInfo>
<title>A Case Study of Deep Learning-Based Multi-Modal Methods for Labeling the Presence of Questionable Content in Movie Trailers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahsa</namePart>
<namePart type="family">Shafaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Smailis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Kakadiaris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we explore different approaches to combine modalities for the problem of automated age-suitability rating of movie trailers. First, we introduce a new dataset containing videos of movie trailers in English downloaded from IMDB and YouTube, along with their corresponding age-suitability rating labels. Secondly, we propose a multi-modal deep learning pipeline addressing the movie trailer age suitability rating problem. This is the first attempt to combine video, audio, and speech information for this problem, and our experimental results show that multi-modal approaches significantly outperform the best mono and bimodal models in this task.</abstract>
<identifier type="citekey">shafaei-etal-2021-case</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.146/</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>1297</start>
<end>1307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Case Study of Deep Learning-Based Multi-Modal Methods for Labeling the Presence of Questionable Content in Movie Trailers
%A Shafaei, Mahsa
%A Smailis, Christos
%A Kakadiaris, Ioannis
%A Solorio, Thamar
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F shafaei-etal-2021-case
%X In this work, we explore different approaches to combine modalities for the problem of automated age-suitability rating of movie trailers. First, we introduce a new dataset containing videos of movie trailers in English downloaded from IMDB and YouTube, along with their corresponding age-suitability rating labels. Secondly, we propose a multi-modal deep learning pipeline addressing the movie trailer age suitability rating problem. This is the first attempt to combine video, audio, and speech information for this problem, and our experimental results show that multi-modal approaches significantly outperform the best mono and bimodal models in this task.
%U https://aclanthology.org/2021.ranlp-1.146/
%P 1297-1307
Markdown (Informal)
[A Case Study of Deep Learning-Based Multi-Modal Methods for Labeling the Presence of Questionable Content in Movie Trailers](https://aclanthology.org/2021.ranlp-1.146/) (Shafaei et al., RANLP 2021)
ACL