Datasets > Modality > Texts > Visual Question Answering (VQA)

Visual Question Answering (VQA) is a dataset containing open-ended questions about images. These questions require an understanding of vision, language and commonsense knowledge to answer. The first version of the dataset was released in October 2015. VQA v2.0 was released in April 2017.

Samples

License

Modalities

Languages

Tasks