@inproceedings{yu-etal-2023-sparse-frame,
title = "Sparse Frame Grouping Network with Action Centered for Untrimmed Video Paragraph Captioning",
author = "Yu, Guorui and
Hu, Yimin and
Zhang, Yuejie and
Feng, Rui and
Zhang, Tao and
Gao, Shang",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.970",
doi = "10.18653/v1/2023.findings-emnlp.970",
pages = "14571--14580",
abstract = "Generating paragraph captions for untrimmed videos without event annotations is challenging, especially when aiming to enhance precision and minimize repetition at the same time. To address this challenge, we propose a module called Sparse Frame Grouping (SFG). It dynamically groups event information with the help of action information for the entire video and excludes redundant frames within pre-defined clips. To enhance the performance, an Intra Contrastive Learning technique is designed to align the SFG module with the core event content in the paragraph, and an Inter Contrastive Learning technique is employed to learn action-guided context with reduced static noise simultaneously. Extensive experiments are conducted on two benchmark datasets (ActivityNet Captions and YouCook2). Results demonstrate that SFG outperforms the state-of-the-art methods on all metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2023-sparse-frame">
<titleInfo>
<title>Sparse Frame Grouping Network with Action Centered for Untrimmed Video Paragraph Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guorui</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yimin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuejie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generating paragraph captions for untrimmed videos without event annotations is challenging, especially when aiming to enhance precision and minimize repetition at the same time. To address this challenge, we propose a module called Sparse Frame Grouping (SFG). It dynamically groups event information with the help of action information for the entire video and excludes redundant frames within pre-defined clips. To enhance the performance, an Intra Contrastive Learning technique is designed to align the SFG module with the core event content in the paragraph, and an Inter Contrastive Learning technique is employed to learn action-guided context with reduced static noise simultaneously. Extensive experiments are conducted on two benchmark datasets (ActivityNet Captions and YouCook2). Results demonstrate that SFG outperforms the state-of-the-art methods on all metrics.</abstract>
<identifier type="citekey">yu-etal-2023-sparse-frame</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.970</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.970</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>14571</start>
<end>14580</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sparse Frame Grouping Network with Action Centered for Untrimmed Video Paragraph Captioning
%A Yu, Guorui
%A Hu, Yimin
%A Zhang, Yuejie
%A Feng, Rui
%A Zhang, Tao
%A Gao, Shang
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F yu-etal-2023-sparse-frame
%X Generating paragraph captions for untrimmed videos without event annotations is challenging, especially when aiming to enhance precision and minimize repetition at the same time. To address this challenge, we propose a module called Sparse Frame Grouping (SFG). It dynamically groups event information with the help of action information for the entire video and excludes redundant frames within pre-defined clips. To enhance the performance, an Intra Contrastive Learning technique is designed to align the SFG module with the core event content in the paragraph, and an Inter Contrastive Learning technique is employed to learn action-guided context with reduced static noise simultaneously. Extensive experiments are conducted on two benchmark datasets (ActivityNet Captions and YouCook2). Results demonstrate that SFG outperforms the state-of-the-art methods on all metrics.
%R 10.18653/v1/2023.findings-emnlp.970
%U https://aclanthology.org/2023.findings-emnlp.970
%U https://doi.org/10.18653/v1/2023.findings-emnlp.970
%P 14571-14580
Markdown (Informal)
[Sparse Frame Grouping Network with Action Centered for Untrimmed Video Paragraph Captioning](https://aclanthology.org/2023.findings-emnlp.970) (Yu et al., Findings 2023)
ACL