BriefGPT.xyz
May, 2022
VQA 可能只需要图片标题
All You May Need for VQA are Image Captions
HTML
PDF
Soravit Changpinyo, Doron Kukliansky, Idan Szpektor, Xi Chen, Nan Ding...
TL;DR
本文提出了使用图像-标题注释与文本问题生成的神经模型自动导出VQA示例的方法，从而改进了VQA数据的质量和量，并在零样本准确性方面取得了双位数的业界领先水平。
Abstract
visual question answering
(
vqa
) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of
→