Search Results for author: Rafał Powalski

Found 2 papers, 1 papers with code

Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer

no code implementations18 Feb 2021 Rafał Powalski, Łukasz Borchmann, Dawid Jurkiewicz, Tomasz Dwojak, Michał Pietruszka, Gabriela Pałka

We address the challenging problem of Natural Language Comprehension beyond plain-text documents by introducing the TILT neural network architecture which simultaneously learns layout information, visual features, and textual semantics.

 Ranked #1 on Visual Question Answering on DocVQA (using extra training data)

Document Image Classification Visual Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.