@inproceedings{feiyu-etal-2024-bridging,
title = "Bridging the Gap between Authentic and Answer-Guided Images for {C}hinese Vision-Language Understanding Enhancement",
author = "Feiyu, Wang and
Wenyu, Guo and
Dong, Yu and
Chen, Kang and
Pengyuan, Liu",
editor = "Lin, Hongfei and
Tan, Hongye and
Li, Bin",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-3.40/",
pages = "353--362",
language = "eng",
abstract = "{\textquotedblleft}The objective of the Chinese Vision-Language Understanding Evaluation (CVLUE) is to comprehensively assess the performance of Chinese vision-language multimodal pre-trained models in multimodal modeling and understanding across four tasks: Image-Text Retrieval, Visual Question Answering, Visual Grounding, and Visual Dialog. To enhance the models' performance across various multimodal tasks, this paper propose a multimodal information understanding enhancement method based on answer-guided images. Firstly, we propose task-specific methods for answer-guided image generation. Secondly, the authentic and answer-guided images are fed into the model for multimodal fine-tuning, respectively. Finally, training objectives are set for different tasks to minimize the gap between the answer-guided images and authentic images, thereby supervising the results produced by the authentic images utlizing answer-guided images. The experimental results demonstrate the effectiveness of the proposed method.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feiyu-etal-2024-bridging">
<titleInfo>
<title>Bridging the Gap between Authentic and Answer-Guided Images for Chinese Vision-Language Understanding Enhancement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Feiyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guo</namePart>
<namePart type="family">Wenyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Pengyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongye</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“The objective of the Chinese Vision-Language Understanding Evaluation (CVLUE) is to comprehensively assess the performance of Chinese vision-language multimodal pre-trained models in multimodal modeling and understanding across four tasks: Image-Text Retrieval, Visual Question Answering, Visual Grounding, and Visual Dialog. To enhance the models’ performance across various multimodal tasks, this paper propose a multimodal information understanding enhancement method based on answer-guided images. Firstly, we propose task-specific methods for answer-guided image generation. Secondly, the authentic and answer-guided images are fed into the model for multimodal fine-tuning, respectively. Finally, training objectives are set for different tasks to minimize the gap between the answer-guided images and authentic images, thereby supervising the results produced by the authentic images utlizing answer-guided images. The experimental results demonstrate the effectiveness of the proposed method.”</abstract>
<identifier type="citekey">feiyu-etal-2024-bridging</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-3.40/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>353</start>
<end>362</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging the Gap between Authentic and Answer-Guided Images for Chinese Vision-Language Understanding Enhancement
%A Feiyu, Wang
%A Wenyu, Guo
%A Dong, Yu
%A Chen, Kang
%A Pengyuan, Liu
%Y Lin, Hongfei
%Y Tan, Hongye
%Y Li, Bin
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F feiyu-etal-2024-bridging
%X “The objective of the Chinese Vision-Language Understanding Evaluation (CVLUE) is to comprehensively assess the performance of Chinese vision-language multimodal pre-trained models in multimodal modeling and understanding across four tasks: Image-Text Retrieval, Visual Question Answering, Visual Grounding, and Visual Dialog. To enhance the models’ performance across various multimodal tasks, this paper propose a multimodal information understanding enhancement method based on answer-guided images. Firstly, we propose task-specific methods for answer-guided image generation. Secondly, the authentic and answer-guided images are fed into the model for multimodal fine-tuning, respectively. Finally, training objectives are set for different tasks to minimize the gap between the answer-guided images and authentic images, thereby supervising the results produced by the authentic images utlizing answer-guided images. The experimental results demonstrate the effectiveness of the proposed method.”
%U https://aclanthology.org/2024.ccl-3.40/
%P 353-362
Markdown (Informal)
[Bridging the Gap between Authentic and Answer-Guided Images for Chinese Vision-Language Understanding Enhancement](https://aclanthology.org/2024.ccl-3.40/) (Feiyu et al., CCL 2024)
ACL