LineEX: Data Extraction from Scientific Line Charts
Abstract
In this paper, we introduce LineEX that extracts data from scientific line charts. We adapt existing vision transformers and pose detection methods and showcase significant performance gains over existing SOTA baselines. We also propose a new loss function and present its effectiveness against existing loss functions. In addition, we synthetically created the largest line chart dataset comprising 430K images. The code and the dataset will be placed in the public domain soon after the acceptance.
Cite
Text
Shivasankaran et al. "LineEX: Data Extraction from Scientific Line Charts." Winter Conference on Applications of Computer Vision, 2023.Markdown
[Shivasankaran et al. "LineEX: Data Extraction from Scientific Line Charts." Winter Conference on Applications of Computer Vision, 2023.](https://mlanthology.org/wacv/2023/p2023wacv-lineex/)BibTeX
@inproceedings{p2023wacv-lineex,
title = {{LineEX: Data Extraction from Scientific Line Charts}},
author = {Shivasankaran, V. P. and Hassan, Muhammad Yusuf and Singh, Mayank},
booktitle = {Winter Conference on Applications of Computer Vision},
year = {2023},
pages = {6213-6221},
url = {https://mlanthology.org/wacv/2023/p2023wacv-lineex/}
}