An End-to-End Multi-Task Learning Model for Image-based Table Recognition

Nam Ly, Atsuhiro Takasu

2023

Abstract

Image-based table recognition is a challenging task due to the diversity of table styles and the complexity of table structures. Most of the previous methods focus on a non-end-to-end approach which divides the problem into two separate sub-problems: table structure recognition; and cell-content recognition and then attempts to solve each sub-problem independently using two separate systems. In this paper, we propose an end-to-end multi-task learning model for image-based table recognition. The proposed model consists of one shared encoder, one shared decoder, and three separate decoders which are used for learning three sub-tasks of table recognition: table structure recognition, cell detection, and cell-content recognition. The whole system can be easily trained and inferred in an end-to-end approach. In the experiments, we evaluate the performance of the proposed model on two large-scale datasets: FinTabNet and PubTabNet. The experiment results show that the proposed model outperforms the state-of-the-art methods in all benchmark datasets.

Paper Citation

in Harvard Style

Ly N. and Takasu A. (2023). An End-to-End Multi-Task Learning Model for Image-based Table Recognition. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 626-634. DOI: 10.5220/0011685000003417

in Bibtex Style

@conference{visapp23,
author={Nam Ly and Atsuhiro Takasu},
title={An End-to-End Multi-Task Learning Model for Image-based Table Recognition},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={626-634},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011685000003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - An End-to-End Multi-Task Learning Model for Image-based Table Recognition
SN - 978-989-758-634-7
AU - Ly N.
AU - Takasu A.
PY - 2023
SP - 626
EP - 634
DO - 10.5220/0011685000003417
PB - SciTePress