1. 假设已有目标
2. 在谷歌用英文关键词搜索
3. 选择引用量最高的文章阅读
4. 通过文章的参考文献或者被引用的文献继续阅读
5. 通常情况下，拿一篇经典文章和一篇最新的优秀文章精读，就足够了

• As a researcher, I adopt a latex template as my resume.

reference: https://www.overleaf.com/latex/templates/resume-chinese/vbrmnfrgbscv

• Additionally, I will build a static GitHub page to show more, e.g., put my presentation video or my paper poster.

reference: https://profiles.stanford.edu/fei-fei-li

Transformer helps your network capture long dependency. It fuses long-distance features with a correlated matrix.

As you know, Convolutional Nerual Network (CNN) is featured with local connection. It is a great prior for low-rank image information. It reduces paramters and suppresses long-distance noise. While it fails to consider long-distance information.

By the way, you can easily get the shortage of Transformer. It has more parameters than CNN, as it need to deal with more features. If your task need long dependency, please use transformer. And vice versa.

I recommand opencv-python for computer vision. You can install it by

pip install opencv-python

OpenCV (Open Source Computer Vision Library: http://opencv.org) is an open-source library that includes several hundreds of computer vision algorithms.

OpenCV has a modular structure, including Core functionality, Image Processing, Video Analysis and etc.

It a excellent python library for research and enginnering.