@inproceedings{baharlouei-etal-2024-labeling,
title = "Labeling Comic Mischief Content in Online Videos with a Multimodal Hierarchical-Cross-Attention Model",
author = "Baharlouei, Elaheh and
Shafaei, Mahsa and
Zhang, Yigeng and
Escalante, Hugo Jair and
Solorio, Thamar",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.874",
pages = "9999--10013",
abstract = "We address the challenge of detecting questionable content in online media, specifically the subcategory of comic mischief. This type of content combines elements such as violence, adult content, or sarcasm with humor, making it difficult to detect. Employing a multimodal approach is vital to capture the subtle details inherent in comic mischief content. To tackle this problem, we propose a novel end-to-end multimodal system for the task of comic mischief detection. As part of this contribution, we release a novel dataset for the targeted task consisting of three modalities: video, text (video captions and subtitles), and audio. We also design a HIerarchical Cross-attention model with CAPtions (HICCAP) to capture the intricate relationships among these modalities. The results show that the proposed approach makes a significant improvement over robust baselines and state-of-the-art models for comic mischief detection and its type classification. This emphasizes the potential of our system to empower users, to make informed decisions about the online content they choose to see.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baharlouei-etal-2024-labeling">
<titleInfo>
<title>Labeling Comic Mischief Content in Online Videos with a Multimodal Hierarchical-Cross-Attention Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elaheh</namePart>
<namePart type="family">Baharlouei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Yigeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="given">Jair</namePart>
<namePart type="family">Escalante</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>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We address the challenge of detecting questionable content in online media, specifically the subcategory of comic mischief. This type of content combines elements such as violence, adult content, or sarcasm with humor, making it difficult to detect. Employing a multimodal approach is vital to capture the subtle details inherent in comic mischief content. To tackle this problem, we propose a novel end-to-end multimodal system for the task of comic mischief detection. As part of this contribution, we release a novel dataset for the targeted task consisting of three modalities: video, text (video captions and subtitles), and audio. We also design a HIerarchical Cross-attention model with CAPtions (HICCAP) to capture the intricate relationships among these modalities. The results show that the proposed approach makes a significant improvement over robust baselines and state-of-the-art models for comic mischief detection and its type classification. This emphasizes the potential of our system to empower users, to make informed decisions about the online content they choose to see.</abstract>
<identifier type="citekey">baharlouei-etal-2024-labeling</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.874</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9999</start>
<end>10013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Labeling Comic Mischief Content in Online Videos with a Multimodal Hierarchical-Cross-Attention Model
%A Baharlouei, Elaheh
%A Shafaei, Mahsa
%A Zhang, Yigeng
%A Escalante, Hugo Jair
%A Solorio, Thamar
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F baharlouei-etal-2024-labeling
%X We address the challenge of detecting questionable content in online media, specifically the subcategory of comic mischief. This type of content combines elements such as violence, adult content, or sarcasm with humor, making it difficult to detect. Employing a multimodal approach is vital to capture the subtle details inherent in comic mischief content. To tackle this problem, we propose a novel end-to-end multimodal system for the task of comic mischief detection. As part of this contribution, we release a novel dataset for the targeted task consisting of three modalities: video, text (video captions and subtitles), and audio. We also design a HIerarchical Cross-attention model with CAPtions (HICCAP) to capture the intricate relationships among these modalities. The results show that the proposed approach makes a significant improvement over robust baselines and state-of-the-art models for comic mischief detection and its type classification. This emphasizes the potential of our system to empower users, to make informed decisions about the online content they choose to see.
%U https://aclanthology.org/2024.lrec-main.874
%P 9999-10013
Markdown (Informal)
[Labeling Comic Mischief Content in Online Videos with a Multimodal Hierarchical-Cross-Attention Model](https://aclanthology.org/2024.lrec-main.874) (Baharlouei et al., LREC-COLING 2024)
ACL