0
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
Yiheng Xu, Minghao Li, Lei Cui et al., 2020. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.
Introduces LayoutLM, a pretrained model that combines the text of scanned documents with its position on the page, aimed at tasks such as extracting information from forms and receipts.
What it's used for here
The emerging-methods survey considers it for layout analysis but notes that it assumes a readable text channel.
Cited by on this site 1 record
1 methods surveys
SRCMathematics
Cite it
Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., & Zhou, M. (2020). LayoutLM: Pre-training of Text and Layout for Document Image Understanding. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. https://doi.org/10.1145/3394486.3403172
@article{xu2020layoutlm,
author = {Xu, Yiheng and Li, Minghao and Cui, Lei and Huang, Shaohan and Wei, Furu and Zhou, Ming},
title = {LayoutLM: Pre-training of Text and Layout for Document Image Understanding},
journal = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
year = {2020},
doi = {10.1145/3394486.3403172},
url = {https://doi.org/10.1145/3394486.3403172}
}TY - JOUR TI - LayoutLM: Pre-training of Text and Layout for Document Image Understanding AU - Xu, Yiheng AU - Li, Minghao AU - Cui, Lei AU - Huang, Shaohan AU - Wei, Furu AU - Zhou, Ming PY - 2020 JO - Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining DO - 10.1145/3394486.3403172 UR - https://doi.org/10.1145/3394486.3403172 ER -
Xu, Yiheng et al.. “LayoutLM: Pre-training of Text and Layout for Document Image Understanding.” Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2020). https://doi.org/10.1145/3394486.3403172.