VQA-E stands for Visual Question Answering with Explanation. It is a visual question answering dataset with explanations. The model involved needs to predict and generate answer explanations. VQA v2 datasetAutomatically derived, a textual analysis is synthesized for each “image-question-answer triad”, making the question-answering process easier to understand and trace.

Citation

@article{li2018vqae, title={VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions}, author={Li, Qing and Tao, Qingyi and Joty, Shafiq and Cai, Jianfei and Luo, Jiebo} journal={ECCV}, year={2018} }