Awesome Self-Supervised Learning / 计算机视觉

Learning to Generate Grounded Image Captions without Localization Supervision

作者：Captions without Localization Supervision, Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib · 来源：arXiv preprint · 类别：其他 · 发布日期：2019-06-01

自监督学习图像表征
新标签打开 AlphaXiv新标签打开 Code
Learning to Generate Grounded Image Captions without Localization Supervision figure
AlphaXiv 中文概览（可滚动查看）