Papers › ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities

ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities

11 Jul 2022SIGIR 2022 7archive 2025-07-28

Paul Lerner, Olivier Ferret, Camille Guinaudeau, Hervé Le Borgne, Romaric Besançon, Jose G Moreno, Jesús Lovón Melgarejo

Whether to retrieve, answer, translate, or reason, multimodality opens up new challenges and perspectives. In this context, we are interested in answering questions about named entities grounded in a visual context using a Knowledge Base (KB). To benchmark this task, called KVQAE (Knowledge-based Visual Question Answering about named Entities), we provide ViQuAE, a dataset of 3.7K questions paired with images. This is the first KVQAE dataset to cover a wide range of entity types (e.g. persons, landmarks, and products). The dataset is annotated using a semi-automatic method. We also propose a KB composed of 1.5M Wikipedia articles paired with images. To set a baseline on the benchmark, we address KVQAE as a two-stage problem: Information Retrieval and Reading Comprehension, with both zero-and few-shot learning methods. The experiments empirically demonstrate the difficulty of the task, especially when questions are not about persons. This work paves the way for better multimodal entity representations and question answering. The dataset, KB, code, and semi-automatic annotation pipeline are freely available at https://github.com/PaulLerner/ViQuAE.

PaperPDFCode

Code

paullerner/viquae mentioned in paperpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ArticlesFew-Shot LearningInformation RetrievalQuestion AnsweringReading ComprehensionRetrievalVisual Question AnsweringVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

ViQuAE

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections