Awesome Self-Supervised Learning / 计算机视觉

Self-supervised learning of visual features through embedding images into text topic spaces

作者：hrough embedding images into text, topic spaces, Lluis Gomez, Yash Patel · 来源：arXiv preprint · 类别：图像表征学习 · 发布日期：2017-05-24

自监督学习表征学习图像表征视频表征自然语言处理
新标签打开 AlphaXiv新标签打开 Code
Self-supervised learning of visual features through embedding images into text topic spaces figure
AlphaXiv 中文概览（可滚动查看）