Salvato in:
Dettagli Bibliografici
Autori principali: Tran, Duong T., Tran, Trung-Kien, Hauswirth, Manfred, Phuoc, Danh Le
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.16403
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908803682795520
author Tran, Duong T.
Tran, Trung-Kien
Hauswirth, Manfred
Phuoc, Danh Le
author_facet Tran, Duong T.
Tran, Trung-Kien
Hauswirth, Manfred
Phuoc, Danh Le
contents In this paper, we propose a new dataset, ReasonVQA, for the Visual Question Answering (VQA) task. Our dataset is automatically integrated with structured encyclopedic knowledge and constructed using a low-cost framework, which is capable of generating complex, multi-hop questions. We evaluated state-of-the-art VQA models on ReasonVQA, and the empirical results demonstrate that ReasonVQA poses significant challenges to these models, highlighting its potential for benchmarking and advancing the field of VQA. Additionally, our dataset can be easily scaled with respect to input images; the current version surpasses the largest existing datasets requiring external knowledge by more than an order of magnitude.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16403
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question Answering
Tran, Duong T.
Tran, Trung-Kien
Hauswirth, Manfred
Phuoc, Danh Le
Computer Vision and Pattern Recognition
In this paper, we propose a new dataset, ReasonVQA, for the Visual Question Answering (VQA) task. Our dataset is automatically integrated with structured encyclopedic knowledge and constructed using a low-cost framework, which is capable of generating complex, multi-hop questions. We evaluated state-of-the-art VQA models on ReasonVQA, and the empirical results demonstrate that ReasonVQA poses significant challenges to these models, highlighting its potential for benchmarking and advancing the field of VQA. Additionally, our dataset can be easily scaled with respect to input images; the current version surpasses the largest existing datasets requiring external knowledge by more than an order of magnitude.
title ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question Answering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.16403