1 code implementation • 11 Feb 2023 • Štěpán Šimsa, Milan Šulc, Michal Uřičář, Yash Patel, Ahmed Hamdi, Matěj Kocián, Matyáš Skalický, Jiří Matas, Antoine Doucet, Mickaël Coustaty, Dimosthenis Karatzas
This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition.
no code implementations • 29 Jan 2023 • Štěpán Šimsa, Milan Šulc, Matyáš Skalický, Yash Patel, Ahmed Hamdi
The DocILE 2023 competition, hosted as a lab at the CLEF 2023 conference and as an ICDAR 2023 competition, will run the first major benchmark for the tasks of Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR) from business documents.
1 code implementation • BMVC 2022 • Vaclav Kosar, Antonín Hoskovec, Milan Šulc, Radek Bartyzal
We introduce GLAMI-1M: the largest multilingual image-text classification dataset and benchmark.
Ranked #1 on Multilingual Image-Text Classification on GLAMI-1M (using extra training data)
2 code implementations • 14 Oct 2022 • Krzysztof Olejniczak, Milan Šulc
While the state-of-the-art methods for in-the-wild text recognition are typically evaluated on complex scenes, their performance in the domain of documents is typically not published, and a comprehensive comparison with methods for document OCR is missing.
Optical Character Recognition Optical Character Recognition (OCR) +1
no code implementations • 20 Jun 2022 • Matyáš Skalický, Štěpán Šimsa, Michal Uřičář, Milan Šulc
Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication.
1 code implementation • 18 Mar 2021 • Lukáš Picek, Milan Šulc, Jiří Matas, Jacob Heilmann-Clausen, Thomas S. Jeppesen, Thomas Læssøe, Tobias Frøslev
Interestingly, ViT achieves results superior to CNN baselines with 80. 45% accuracy and 0. 743 macro F1 score, reducing the CNN error by 9% and 12% respectively.
Ranked #1 on Image Classification on DF20