Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/hoya012/CVPR-2019-Paper-Statistics

Statistics and Visualization of acceptance rate, main keyword of CVPR 2019 accepted papers for the main Computer Vision conference (CVPR)
https://github.com/hoya012/CVPR-2019-Paper-Statistics

cvpr cvpr2019 paper paper-analysis statistics

Last synced: 26 days ago
JSON representation

Statistics and Visualization of acceptance rate, main keyword of CVPR 2019 accepted papers for the main Computer Vision conference (CVPR)

Host: GitHub
URL: https://github.com/hoya012/CVPR-2019-Paper-Statistics
Owner: hoya012
Created: 2019-04-16T01:18:27.000Z (over 5 years ago)
Default Branch: master
Last Pushed: 2019-06-10T04:24:55.000Z (over 5 years ago)
Last Synced: 2024-08-07T23:13:00.770Z (5 months ago)
Topics: cvpr, cvpr2019, paper, paper-analysis, statistics
Language: Jupyter Notebook
Homepage:
Size: 2.9 MB
Stars: 533
Watchers: 19
Forks: 101
Open Issues: 1
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

        # CVPR-Paper-Statistics

Statistics and Visualization of acceptance rate, main keyword of CVPR 2019 accepted papers for the main Computer Vision conference [(CVPR 2019)](http://cvpr2019.thecvf.com/)

Inspired by [`ICLR2019-OpenReviewData`](https://github.com/shaohua0116/ICLR2019-OpenReviewData)



  



# CVPR 2019 Acceptance rate (2015~2019)

- The total number of papers is increasing every year and this year has increased significantly!

- The acceptance rate decreased from 30% to 25%.



  



# CVPR 2019 simple paper review(20 papers)

- [Slide](https://www.slideshare.net/HoseongLee6/2019-cvpr-paperoverview)

# CVPR Paper Keywords statistics

- [Accepted Paper list](https://github.com/hoya012/CVPR-Paper-Statistics/blob/master/2019_cvpr/cvpr_2019_poster.csv)

- Most of the top keywords were maintained

   - Image, detection, 3d, object, video, segmentation, adversarial, recognition, visual …

- `graph`, `cloud`, `representation` are about twice as frequent

   - graph : 15 -> 45

   - representation: 25 -> 48

   - cloud: 16 -> 35



  



# Analysis and Visualization Code (Jupyter Notebook)

- The above data can be obtained from a simple jupyter notebook script.

- I wrote two versions of the code.

   - [`CVPR_paper_statistics_using_csv.ipynb`](https://github.com/hoya012/CVPR-Paper-Statistics/blob/master/CVPR_paper_statistics_using_csv.ipynb) --> Use csv data format

   - [`CVPR_paper_statistics_using_chrome.ipynb`](https://github.com/hoya012/CVPR-Paper-Statistics/blob/master/CVPR_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**