VQA 2.0

VQA-2.0 is a benchmark dataset that contains images paired with questions and answers, used to evaluate the performance of models in visual question answering tasks.

Papers using VQA 2.0 (4)

Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering2022 · 16 citesMixGen: A New Multi-Modal Data Augmentation2022 · 2 citesCompound Tokens: Channel Fusion for Vision-Language Representation Learning2022 · 2 citesVQA with Cascade of Self- and Co-Attention Blocks2023