@inproceedings{liu-wan-2021-video,
title = "Video Paragraph Captioning as a Text Summarization Task",
author = "Liu, Hui and
Wan, Xiaojun",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.9",
doi = "10.18653/v1/2021.acl-short.9",
pages = "55--60",
abstract = "Video paragraph captioning aims to generate a set of coherent sentences to describe a video that contains several events. Most previous methods simplify this task by using ground-truth event segments. In this work, we propose a novel framework by taking this task as a text summarization task. We first generate lots of sentence-level captions focusing on different video clips and then summarize these captions to obtain the final paragraph caption. Our method does not depend on ground-truth event segments. Experiments on two popular datasets ActivityNet Captions and YouCookII demonstrate the advantages of our new framework. On the ActivityNet dataset, our method even outperforms some previous methods using ground-truth event segment labels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-wan-2021-video">
<titleInfo>
<title>Video Paragraph Captioning as a Text Summarization Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Video paragraph captioning aims to generate a set of coherent sentences to describe a video that contains several events. Most previous methods simplify this task by using ground-truth event segments. In this work, we propose a novel framework by taking this task as a text summarization task. We first generate lots of sentence-level captions focusing on different video clips and then summarize these captions to obtain the final paragraph caption. Our method does not depend on ground-truth event segments. Experiments on two popular datasets ActivityNet Captions and YouCookII demonstrate the advantages of our new framework. On the ActivityNet dataset, our method even outperforms some previous methods using ground-truth event segment labels.</abstract>
<identifier type="citekey">liu-wan-2021-video</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.9</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.9</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>55</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Video Paragraph Captioning as a Text Summarization Task
%A Liu, Hui
%A Wan, Xiaojun
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F liu-wan-2021-video
%X Video paragraph captioning aims to generate a set of coherent sentences to describe a video that contains several events. Most previous methods simplify this task by using ground-truth event segments. In this work, we propose a novel framework by taking this task as a text summarization task. We first generate lots of sentence-level captions focusing on different video clips and then summarize these captions to obtain the final paragraph caption. Our method does not depend on ground-truth event segments. Experiments on two popular datasets ActivityNet Captions and YouCookII demonstrate the advantages of our new framework. On the ActivityNet dataset, our method even outperforms some previous methods using ground-truth event segment labels.
%R 10.18653/v1/2021.acl-short.9
%U https://aclanthology.org/2021.acl-short.9
%U https://doi.org/10.18653/v1/2021.acl-short.9
%P 55-60
Markdown (Informal)
[Video Paragraph Captioning as a Text Summarization Task](https://aclanthology.org/2021.acl-short.9) (Liu & Wan, ACL-IJCNLP 2021)
ACL
- Hui Liu and Xiaojun Wan. 2021. Video Paragraph Captioning as a Text Summarization Task. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 55–60, Online. Association for Computational Linguistics.