Member-only story
Discovering Hidden Semantic Structures in CVPR 2023 Papers
A discussion about Web scraping, Topic Modelling, and Semantic Search
Introduction
CVPR is around the corner and I decided to look at the papers and narrow down the ones I’m interested in. CVPR stands for “Computer Vision and Pattern Recognition Conference”. It is an annual conference and is regarded as one of the most important conferences in the field. According to Google Scholar Metrics (2022), it is the highest-impact computing venue [1]. The conference comprises the main conference and several co-located workshops and short courses [2].
I must admit that I started the paper discovery process quite late. Nonetheless, I began with the following steps:
- Open the list of papers filtered by day e.g. CVPR 2023 Open Access Repository (day 1)
- Manually go through the titles sequentially.
- Skim through the abstract of the titles that look interesting.
- Add interesting papers to my read list based on the abstract.
After going through ~50 titles and ~25 abstracts I was saturated and wanted to take a break. That’s when I decided to scroll to the end quickly and realized that I would not be able to go through all the titles.
