https://github.com/hoya012/cvpr-2021-paper-statistics
Statistics and Visualization of acceptance rate, main keyword of CVPR 2021 accepted papers for the main Computer Vision conference (CVPR)
https://github.com/hoya012/cvpr-2021-paper-statistics
Last synced: 5 months ago
JSON representation
Statistics and Visualization of acceptance rate, main keyword of CVPR 2021 accepted papers for the main Computer Vision conference (CVPR)
- Host: GitHub
- URL: https://github.com/hoya012/cvpr-2021-paper-statistics
- Owner: hoya012
- Created: 2021-05-24T07:53:57.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-05-24T08:17:16.000Z (over 4 years ago)
- Last Synced: 2025-06-06T17:09:16.039Z (6 months ago)
- Language: Jupyter Notebook
- Size: 1.58 MB
- Stars: 79
- Watchers: 3
- Forks: 10
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# CVPR-2021 Paper-Statistics
Statistics and Visualization of acceptance rate, main keyword of CVPR 2021 accepted papers for the main Computer Vision conference [(CVPR 2021)](http://cvpr2021.thecvf.com/)
Inspired by [`CVPR-2020-Paper-Statistics`](https://github.com/hoya012/CVPR-2020-Paper-Statistics)
# CVPR 2021 Acceptance rate (2017~2021)
- The total number of papers is increasing every year and this year has increased significantly!
- The acceptance rate decreased from 25% to 22%.
# CVPR 2021 Paper Keywords statistics
- Most of the top keywords were maintained
- Image, detection, 3d, object, video, segmentation, etc.
- `unsupervised`, `self-supervised`, `semi-supervised` are about x1.5 as frequent
- unsupervised : 52 -> 77
- self-supervised: 33 -> 50
- semi-supervised: 25 -> 35
# Analysis and Visualization Code (Jupyter Notebook)
- The above data can be obtained from a simple jupyter notebook script.
- [`CVPR_paper_statistics_using_chrome.ipynb`](https://github.com/hoya012/CVPR-2021-Paper-Statistics/blob/main/CVPR2021_paper_statistics_using_chrome.ipynb) --> Use website data format
## Prerequisites
- python3.5
- [selenium](https://selenium-python.readthedocs.io/)
- [wordcloud](https://pypi.org/project/wordcloud/)
- [matplotlib](https://matplotlib.org/)
or
**i highly recommend to use** [google colab](https://colab.research.google.com/)
Just **download jupyter notebook** and **move to your google drive** and **Open with Colaboratory**