a public good project by the
Synthesis
Company
of California

© 2026

A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge | doi.page

0 citations0 references

Google Scholar doi.org

A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge

Lecture notes in computer science·2022·pp. 146–162

Citations Over TimeTop 1% of 2022 papers

Dustin Schwenk, Apoorv Khandelwal, Christopher Clark, Kenneth Marino, Roozbeh Mottaghi

Related Papers

Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches(2019)
→ Multi-Level Knowledge Injecting for Visual Commonsense Reasoning(2020)40 cited
→ Choice-Driven Contextual Reasoning for Commonsense Question Answering(2022)3 cited
→ Natural Language Processing with Commonsense Knowledge: A Survey(2021)9 cited
→ A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge(2022)1 cited