@inproceedings{takahashi-etal-2024-abstractive,
title = "Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation",
author = "Takahashi, Rikito and
Kiyomaru, Hirokazu and
Chu, Chenhui and
Kurohashi, Sadao",
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.5",
pages = "57--69",
abstract = "This paper introduces a new task, abstractive multi-video captioning, which focuses on abstracting multiple videos with natural language. Unlike conventional video captioning tasks generating a specific caption for a video, our task generates an abstract caption of the shared content in a video group containing multiple videos. To address our task, models must learn to understand each video in detail and have strong abstraction abilities to find commonalities among videos. We construct a benchmark dataset for abstractive multi-video captioning named AbstrActs. AbstrActs contains 13.5k video groups and corresponding abstract captions. As abstractive multi-video captioning models, we explore two approaches: end-to-end and cascade. For evaluation, we proposed a new metric, CocoA, which can evaluate the model performance based on the abstractness of the generated captions. In experiments, we report the impact of the way of combining multiple video features, the overall model architecture, and the number of input videos.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takahashi-etal-2024-abstractive">
<titleInfo>
<title>Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rikito</namePart>
<namePart type="family">Takahashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hirokazu</namePart>
<namePart type="family">Kiyomaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</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>This paper introduces a new task, abstractive multi-video captioning, which focuses on abstracting multiple videos with natural language. Unlike conventional video captioning tasks generating a specific caption for a video, our task generates an abstract caption of the shared content in a video group containing multiple videos. To address our task, models must learn to understand each video in detail and have strong abstraction abilities to find commonalities among videos. We construct a benchmark dataset for abstractive multi-video captioning named AbstrActs. AbstrActs contains 13.5k video groups and corresponding abstract captions. As abstractive multi-video captioning models, we explore two approaches: end-to-end and cascade. For evaluation, we proposed a new metric, CocoA, which can evaluate the model performance based on the abstractness of the generated captions. In experiments, we report the impact of the way of combining multiple video features, the overall model architecture, and the number of input videos.</abstract>
<identifier type="citekey">takahashi-etal-2024-abstractive</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.5</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>57</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation
%A Takahashi, Rikito
%A Kiyomaru, Hirokazu
%A Chu, Chenhui
%A Kurohashi, Sadao
%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 takahashi-etal-2024-abstractive
%X This paper introduces a new task, abstractive multi-video captioning, which focuses on abstracting multiple videos with natural language. Unlike conventional video captioning tasks generating a specific caption for a video, our task generates an abstract caption of the shared content in a video group containing multiple videos. To address our task, models must learn to understand each video in detail and have strong abstraction abilities to find commonalities among videos. We construct a benchmark dataset for abstractive multi-video captioning named AbstrActs. AbstrActs contains 13.5k video groups and corresponding abstract captions. As abstractive multi-video captioning models, we explore two approaches: end-to-end and cascade. For evaluation, we proposed a new metric, CocoA, which can evaluate the model performance based on the abstractness of the generated captions. In experiments, we report the impact of the way of combining multiple video features, the overall model architecture, and the number of input videos.
%U https://aclanthology.org/2024.lrec-main.5
%P 57-69
Markdown (Informal)
[Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation](https://aclanthology.org/2024.lrec-main.5) (Takahashi et al., LREC-COLING 2024)
ACL