@inproceedings{wu-etal-2023-diffuvst,
title = "{D}iffu{VST}: Narrating Fictional Scenes with Global-History-Guided Denoising Models",
author = "Wu, Shengguang and
Yuan, Mei and
Su, Qi",
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.126",
doi = "10.18653/v1/2023.findings-emnlp.126",
pages = "1885--1896",
abstract = "Recent advances in image and video creation, especially AI-based image synthesis, have led to the production of numerous visual scenes that exhibit a high level of abstractness and diversity. Consequently, Visual Storytelling (VST), a task that involves generating meaningful and coherent narratives from a collection of images, has become even more challenging and is increasingly desired beyond real-world imagery. While existing VST techniques, which typically use autoregressive decoders, have made significant progress, they suffer from low inference speed and are not well-suited for synthetic scenes. To this end, we propose a novel diffusion-based system DiffuVST, which models the generation of a series of visual descriptions as a single conditional denoising process. The stochastic and non-autoregressive nature of DiffuVST at inference time allows it to generate highly diverse narratives more efficiently. In addition, DiffuVST features a unique design with bi-directional text history guidance and multimodal adapter modules, which effectively improve inter-sentence coherence and image-to-text fidelity. Extensive experiments on the story generation task covering four fictional visual-story datasets demonstrate the superiority of DiffuVST over traditional autoregressive models in terms of both text quality and inference speed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-diffuvst">
<titleInfo>
<title>DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shengguang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Su</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>Recent advances in image and video creation, especially AI-based image synthesis, have led to the production of numerous visual scenes that exhibit a high level of abstractness and diversity. Consequently, Visual Storytelling (VST), a task that involves generating meaningful and coherent narratives from a collection of images, has become even more challenging and is increasingly desired beyond real-world imagery. While existing VST techniques, which typically use autoregressive decoders, have made significant progress, they suffer from low inference speed and are not well-suited for synthetic scenes. To this end, we propose a novel diffusion-based system DiffuVST, which models the generation of a series of visual descriptions as a single conditional denoising process. The stochastic and non-autoregressive nature of DiffuVST at inference time allows it to generate highly diverse narratives more efficiently. In addition, DiffuVST features a unique design with bi-directional text history guidance and multimodal adapter modules, which effectively improve inter-sentence coherence and image-to-text fidelity. Extensive experiments on the story generation task covering four fictional visual-story datasets demonstrate the superiority of DiffuVST over traditional autoregressive models in terms of both text quality and inference speed.</abstract>
<identifier type="citekey">wu-etal-2023-diffuvst</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.126</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.126</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>1885</start>
<end>1896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models
%A Wu, Shengguang
%A Yuan, Mei
%A Su, Qi
%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 wu-etal-2023-diffuvst
%X Recent advances in image and video creation, especially AI-based image synthesis, have led to the production of numerous visual scenes that exhibit a high level of abstractness and diversity. Consequently, Visual Storytelling (VST), a task that involves generating meaningful and coherent narratives from a collection of images, has become even more challenging and is increasingly desired beyond real-world imagery. While existing VST techniques, which typically use autoregressive decoders, have made significant progress, they suffer from low inference speed and are not well-suited for synthetic scenes. To this end, we propose a novel diffusion-based system DiffuVST, which models the generation of a series of visual descriptions as a single conditional denoising process. The stochastic and non-autoregressive nature of DiffuVST at inference time allows it to generate highly diverse narratives more efficiently. In addition, DiffuVST features a unique design with bi-directional text history guidance and multimodal adapter modules, which effectively improve inter-sentence coherence and image-to-text fidelity. Extensive experiments on the story generation task covering four fictional visual-story datasets demonstrate the superiority of DiffuVST over traditional autoregressive models in terms of both text quality and inference speed.
%R 10.18653/v1/2023.findings-emnlp.126
%U https://aclanthology.org/2023.findings-emnlp.126
%U https://doi.org/10.18653/v1/2023.findings-emnlp.126
%P 1885-1896
Markdown (Informal)
[DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models](https://aclanthology.org/2023.findings-emnlp.126) (Wu et al., Findings 2023)
ACL