Abstract

We will present the individual task in the area of Visual Document Understanding. We will show this theoretical task on the practical need for Intelligent Back Office. We will describe interesting approaches that combine the information from Images and Text.

Presentation

Visual Document Understanding

Slides presented at the seminar on April 14, 2022

Readings

1. Xang, Y. (2020). LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding (https://arxiv.org/abs/2012.14740)
2. Kim, G. (2022). Donut: Document Understanding Transformer without OCR
   (https://arxiv.org/abs/2111.15664)
3. Li, M (2021). TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
   (https://arxiv.org/abs/2109.10282)