@article{hong-etal-2023-visual-writing,
title = "Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences",
author = "Hong, Xudong and
Sayeed, Asad and
Mehra, Khushboo and
Demberg, Vera and
Schiele, Bernt",
journal = "Transactions of the Association for Computational Linguistics",
volume = "11",
year = "2023",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2023.tacl-1.33",
doi = "10.1162/tacl_a_00553",
pages = "565--581",
abstract = "Current work on image-based story generation suffers from the fact that the existing image sequence collections do not have coherent plots behind them. We improve visual story generation by producing a new image-grounded dataset, Visual Writing Prompts (VWP). VWP contains almost 2K selected sequences of movie shots, each including 5-10 images. The image sequences are aligned with a total of 12K stories which were collected via crowdsourcing given the image sequences and a set of grounded characters from the corresponding image sequence. Our new image sequence collection and filtering process has allowed us to obtain stories that are more coherent, diverse, and visually grounded compared to previous work. We also propose a character-based story generation model driven by coherence as a strong baseline. Evaluations show that our generated stories are more coherent, visually grounded, and diverse than stories generated with the current state-of-the-art model. Our code, image features, annotations and collected stories are available at \url{https://vwprompt.github.io/}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-etal-2023-visual-writing">
<titleInfo>
<title>Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asad</namePart>
<namePart type="family">Sayeed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushboo</namePart>
<namePart type="family">Mehra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernt</namePart>
<namePart type="family">Schiele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Current work on image-based story generation suffers from the fact that the existing image sequence collections do not have coherent plots behind them. We improve visual story generation by producing a new image-grounded dataset, Visual Writing Prompts (VWP). VWP contains almost 2K selected sequences of movie shots, each including 5-10 images. The image sequences are aligned with a total of 12K stories which were collected via crowdsourcing given the image sequences and a set of grounded characters from the corresponding image sequence. Our new image sequence collection and filtering process has allowed us to obtain stories that are more coherent, diverse, and visually grounded compared to previous work. We also propose a character-based story generation model driven by coherence as a strong baseline. Evaluations show that our generated stories are more coherent, visually grounded, and diverse than stories generated with the current state-of-the-art model. Our code, image features, annotations and collected stories are available at https://vwprompt.github.io/.</abstract>
<identifier type="citekey">hong-etal-2023-visual-writing</identifier>
<identifier type="doi">10.1162/tacl_a_00553</identifier>
<location>
<url>https://aclanthology.org/2023.tacl-1.33</url>
</location>
<part>
<date>2023</date>
<detail type="volume"><number>11</number></detail>
<extent unit="page">
<start>565</start>
<end>581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences
%A Hong, Xudong
%A Sayeed, Asad
%A Mehra, Khushboo
%A Demberg, Vera
%A Schiele, Bernt
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F hong-etal-2023-visual-writing
%X Current work on image-based story generation suffers from the fact that the existing image sequence collections do not have coherent plots behind them. We improve visual story generation by producing a new image-grounded dataset, Visual Writing Prompts (VWP). VWP contains almost 2K selected sequences of movie shots, each including 5-10 images. The image sequences are aligned with a total of 12K stories which were collected via crowdsourcing given the image sequences and a set of grounded characters from the corresponding image sequence. Our new image sequence collection and filtering process has allowed us to obtain stories that are more coherent, diverse, and visually grounded compared to previous work. We also propose a character-based story generation model driven by coherence as a strong baseline. Evaluations show that our generated stories are more coherent, visually grounded, and diverse than stories generated with the current state-of-the-art model. Our code, image features, annotations and collected stories are available at https://vwprompt.github.io/.
%R 10.1162/tacl_a_00553
%U https://aclanthology.org/2023.tacl-1.33
%U https://doi.org/10.1162/tacl_a_00553
%P 565-581
Markdown (Informal)
[Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences](https://aclanthology.org/2023.tacl-1.33) (Hong et al., TACL 2023)
ACL