Human-Adversarial Visual Question Answering Sasha Sheng Amanpreet Singh V edanuj Goswami Jose Alberto Lopez Magana Tristan Thrush Wojciech Galuba Devi Parikh Douwe Kiela

Aug-16-2025, 16:16:54 GMT–Neural Information Processing Systems 

Performance on the most commonly used Visual Question Answering dataset (VQA v2) is starting to approach human accuracy.