@inproceedings{qian-etal-2024-anytrans,
title = "{A}ny{T}rans: Translate {A}ny{T}ext in the Image with Large Scale Models",
author = "Qian, Zhipeng and
Zhang, Pei and
Yang, Baosong and
Fan, Kai and
Ma, Yiwei and
Wong, Derek F. and
Sun, Xiaoshuai and
Ji, Rongrong",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.137/",
doi = "10.18653/v1/2024.findings-emnlp.137",
pages = "2432--2444",
abstract = "This paper introduces AnyText, an all-encompassing framework for the task{--}In-Image Machine Translation (IIMT), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, diffusion models' advanced inpainting and editing abilities make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the IIMT task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-etal-2024-anytrans">
<titleInfo>
<title>AnyTrans: Translate AnyText in the Image with Large Scale Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baosong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoshuai</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongrong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces AnyText, an all-encompassing framework for the task–In-Image Machine Translation (IIMT), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, diffusion models’ advanced inpainting and editing abilities make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the IIMT task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs.</abstract>
<identifier type="citekey">qian-etal-2024-anytrans</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.137</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.137/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>2432</start>
<end>2444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AnyTrans: Translate AnyText in the Image with Large Scale Models
%A Qian, Zhipeng
%A Zhang, Pei
%A Yang, Baosong
%A Fan, Kai
%A Ma, Yiwei
%A Wong, Derek F.
%A Sun, Xiaoshuai
%A Ji, Rongrong
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F qian-etal-2024-anytrans
%X This paper introduces AnyText, an all-encompassing framework for the task–In-Image Machine Translation (IIMT), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, diffusion models’ advanced inpainting and editing abilities make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the IIMT task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs.
%R 10.18653/v1/2024.findings-emnlp.137
%U https://aclanthology.org/2024.findings-emnlp.137/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.137
%P 2432-2444
Markdown (Informal)
[AnyTrans: Translate AnyText in the Image with Large Scale Models](https://aclanthology.org/2024.findings-emnlp.137/) (Qian et al., Findings 2024)
ACL
- Zhipeng Qian, Pei Zhang, Baosong Yang, Kai Fan, Yiwei Ma, Derek F. Wong, Xiaoshuai Sun, and Rongrong Ji. 2024. AnyTrans: Translate AnyText in the Image with Large Scale Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2432–2444, Miami, Florida, USA. Association for Computational Linguistics.