google-research-datasets / vrduLinks
We identify the desiderata for a comprehensive benchmark and propose Visually Rich Document Understanding (VRDU). VRDU contains two datasets that represent several challenges: rich schema including diverse data types, complex templates, and diversity of layouts within a single document type.
☆80Updated 2 years ago
Alternatives and similar repositories for vrdu
Users that are interested in vrdu are comparing it to the libraries listed below
Sorting:
- ☆32Updated last year
- ReadingBank: A Benchmark Dataset for Reading Order Detection☆109Updated last year
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆130Updated 2 years ago
- ☆249Updated 2 years ago
- Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task…☆283Updated 2 years ago
- InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)☆161Updated last year
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆199Updated 5 months ago
- The code related to the baselines from NeurIPS 2021 paper "DUE: End-to-End Document Understanding Benchmark."☆36Updated 2 years ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆148Updated 3 months ago
- ☆45Updated 3 years ago
- OCR Annotations from Amazon Textract for Industry Documents Library☆103Updated 3 years ago
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆52Updated 2 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆134Updated last year
- ☆66Updated last year
- Official implementation for Dessurt: Document end-to-end self-supervised understanding and recognition transformer☆62Updated 2 years ago
- ☆159Updated 2 years ago
- CTE: Contextualized Table Extraction Dataset☆17Updated 2 years ago
- My implementation of Kosmos2.5 from the paper: "KOSMOS-2.5: A Multimodal Literate Model"☆73Updated last week
- Dataset and scripts for HRDoc☆38Updated 2 years ago
- High-Performance Transformers for Table Structure Recognition Need Early Convolutions☆45Updated last year
- The WordScape repository contains code for the WordScape pipeline to create datasets to train document understanding models.☆37Updated last year
- multimodal document analysis☆164Updated last year
- Document Visual Question Answering☆123Updated 5 years ago
- Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understan…☆351Updated 2 years ago
- Incorporating VIsual LAyout Structures for Scientific Text Classification☆179Updated 2 years ago
- SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)☆92Updated 4 months ago
- An unofficial Implementation of DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents☆37Updated last year
- ☆22Updated 4 years ago
- Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models, EMNLP 2023☆46Updated last year
- Index of URLs to pdf files all over the internet and scripts☆24Updated 2 years ago