@inproceedings{yang-etal-2024-synchronized,
title = "Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline",
author = "Yang, Dingyi and
Zhan, Chunru and
Wang, Ziheng and
Wang, Biao and
Ge, Tiezheng and
Zheng, Bo and
Jin, Qin",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.513",
doi = "10.18653/v1/2024.acl-long.513",
pages = "9479--9493",
abstract = "Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to share a story and attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video captioning and video story generation have made some progress. However, in practical applications, we typically require synchronized narrations for ongoing visual scenes. In this work, we introduce a new task of Synchronized Video Storytelling, which aims to generate synchronous and informative narrations for videos. These narrations, associated with each video clip, should relate to the visual content, integrate relevant knowledge, and have an appropriate word count corresponding to the clip{'}s duration. Specifically, a structured storyline is beneficial to guide the generation process, ensuring coherence and integrity. To support the exploration of this task, we introduce a new benchmark dataset E-SyncVidStory with rich annotations. Since existing Multimodal LLMs are not effective in addressing this task in one-shot or few-shot settings, we propose a framework named VideoNarrator that can generate a storyline for input videos and simultaneously generate narrations with the guidance of the generated or predefined storyline. We further introduce a set of evaluation metrics to thoroughly assess the generation. Both automatic and human evaluations validate the effectiveness of our approach. Our dataset, codes, and evaluations will be released.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-synchronized">
<titleInfo>
<title>Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dingyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunru</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiezheng</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to share a story and attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video captioning and video story generation have made some progress. However, in practical applications, we typically require synchronized narrations for ongoing visual scenes. In this work, we introduce a new task of Synchronized Video Storytelling, which aims to generate synchronous and informative narrations for videos. These narrations, associated with each video clip, should relate to the visual content, integrate relevant knowledge, and have an appropriate word count corresponding to the clip’s duration. Specifically, a structured storyline is beneficial to guide the generation process, ensuring coherence and integrity. To support the exploration of this task, we introduce a new benchmark dataset E-SyncVidStory with rich annotations. Since existing Multimodal LLMs are not effective in addressing this task in one-shot or few-shot settings, we propose a framework named VideoNarrator that can generate a storyline for input videos and simultaneously generate narrations with the guidance of the generated or predefined storyline. We further introduce a set of evaluation metrics to thoroughly assess the generation. Both automatic and human evaluations validate the effectiveness of our approach. Our dataset, codes, and evaluations will be released.</abstract>
<identifier type="citekey">yang-etal-2024-synchronized</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.513</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.513</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>9479</start>
<end>9493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline
%A Yang, Dingyi
%A Zhan, Chunru
%A Wang, Ziheng
%A Wang, Biao
%A Ge, Tiezheng
%A Zheng, Bo
%A Jin, Qin
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F yang-etal-2024-synchronized
%X Video storytelling is engaging multimedia content that utilizes video and its accompanying narration to share a story and attract the audience, where a key challenge is creating narrations for recorded visual scenes. Previous studies on dense video captioning and video story generation have made some progress. However, in practical applications, we typically require synchronized narrations for ongoing visual scenes. In this work, we introduce a new task of Synchronized Video Storytelling, which aims to generate synchronous and informative narrations for videos. These narrations, associated with each video clip, should relate to the visual content, integrate relevant knowledge, and have an appropriate word count corresponding to the clip’s duration. Specifically, a structured storyline is beneficial to guide the generation process, ensuring coherence and integrity. To support the exploration of this task, we introduce a new benchmark dataset E-SyncVidStory with rich annotations. Since existing Multimodal LLMs are not effective in addressing this task in one-shot or few-shot settings, we propose a framework named VideoNarrator that can generate a storyline for input videos and simultaneously generate narrations with the guidance of the generated or predefined storyline. We further introduce a set of evaluation metrics to thoroughly assess the generation. Both automatic and human evaluations validate the effectiveness of our approach. Our dataset, codes, and evaluations will be released.
%R 10.18653/v1/2024.acl-long.513
%U https://aclanthology.org/2024.acl-long.513
%U https://doi.org/10.18653/v1/2024.acl-long.513
%P 9479-9493
Markdown (Informal)
[Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline](https://aclanthology.org/2024.acl-long.513) (Yang et al., ACL 2024)
ACL