VQA: Visual Question Answering

@article{Antol2015VQAVQ,
  title={VQA: Visual Question Answering},
  author={Stanislaw Antol and Aishwarya Agrawal and Jiasen Lu and Margaret Mitchell and Dhruv Batra and C. Lawrence Zitnick and Devi Parikh},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={2425-2433}
}
We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs… CONTINUE READING
Tweets
This paper has been referenced on Twitter 53 times. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.