Visual Question Answering

홈페이지 · 논문 1,834편

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](/dataset/visual-question-answering-v2-0) was released in April 2017.