@inproceedings{shi-etal-2024-find-common,
title = "Find-the-Common: A Benchmark for Explaining Visual Patterns from Images",
author = "Shi, Yuting and
Inoue, Naoya and
Wei, Houjing and
Zhao, Yufeng and
Jin, Tao",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.642",
pages = "7307--7313",
abstract = "Recent advances in Instruction-fine-tuned Vision and Language Models (IVLMs), such as GPT-4V and InstructBLIP, have prompted some studies have started an in-depth analysis of the reasoning capabilities of IVLMs. However, Inductive Visual Reasoning, a vital skill for text-image understanding, remains underexplored due to the absence of benchmarks. In this paper, we introduce Find-the-Common (FTC): a new vision and language task for Inductive Visual Reasoning. In this task, models are required to identify an answer that explains the common attributes across visual scenes. We create a new dataset for the FTC and assess the performance of several contemporary approaches including Image-Based Reasoning, Text-Based Reasoning, and Image-Text-Based Reasoning with various models. Extensive experiments show that even state-of-the-art models like GPT-4V can only archive with 48{\%} accuracy on the FTC, for which, the FTC is a new challenge for the visual reasoning research community. Our dataset has been released and is available online: https://github.com/SSSSSeki/Find-the-common.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2024-find-common">
<titleInfo>
<title>Find-the-Common: A Benchmark for Explaining Visual Patterns from Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuting</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoya</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houjing</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in Instruction-fine-tuned Vision and Language Models (IVLMs), such as GPT-4V and InstructBLIP, have prompted some studies have started an in-depth analysis of the reasoning capabilities of IVLMs. However, Inductive Visual Reasoning, a vital skill for text-image understanding, remains underexplored due to the absence of benchmarks. In this paper, we introduce Find-the-Common (FTC): a new vision and language task for Inductive Visual Reasoning. In this task, models are required to identify an answer that explains the common attributes across visual scenes. We create a new dataset for the FTC and assess the performance of several contemporary approaches including Image-Based Reasoning, Text-Based Reasoning, and Image-Text-Based Reasoning with various models. Extensive experiments show that even state-of-the-art models like GPT-4V can only archive with 48% accuracy on the FTC, for which, the FTC is a new challenge for the visual reasoning research community. Our dataset has been released and is available online: https://github.com/SSSSSeki/Find-the-common.</abstract>
<identifier type="citekey">shi-etal-2024-find-common</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.642</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7307</start>
<end>7313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Find-the-Common: A Benchmark for Explaining Visual Patterns from Images
%A Shi, Yuting
%A Inoue, Naoya
%A Wei, Houjing
%A Zhao, Yufeng
%A Jin, Tao
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F shi-etal-2024-find-common
%X Recent advances in Instruction-fine-tuned Vision and Language Models (IVLMs), such as GPT-4V and InstructBLIP, have prompted some studies have started an in-depth analysis of the reasoning capabilities of IVLMs. However, Inductive Visual Reasoning, a vital skill for text-image understanding, remains underexplored due to the absence of benchmarks. In this paper, we introduce Find-the-Common (FTC): a new vision and language task for Inductive Visual Reasoning. In this task, models are required to identify an answer that explains the common attributes across visual scenes. We create a new dataset for the FTC and assess the performance of several contemporary approaches including Image-Based Reasoning, Text-Based Reasoning, and Image-Text-Based Reasoning with various models. Extensive experiments show that even state-of-the-art models like GPT-4V can only archive with 48% accuracy on the FTC, for which, the FTC is a new challenge for the visual reasoning research community. Our dataset has been released and is available online: https://github.com/SSSSSeki/Find-the-common.
%U https://aclanthology.org/2024.lrec-main.642
%P 7307-7313
Markdown (Informal)
[Find-the-Common: A Benchmark for Explaining Visual Patterns from Images](https://aclanthology.org/2024.lrec-main.642) (Shi et al., LREC-COLING 2024)
ACL