google-research-datasets / vrdu
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.
☆77Updated 2 years ago
Alternatives and similar repositories for vrdu:
Users that are interested in vrdu are comparing it to the libraries listed below
- The code related to the baselines from NeurIPS 2021 paper "DUE: End-to-End Document Understanding Benchmark."☆36Updated last year
- ReadingBank: A Benchmark Dataset for Reading Order Detection☆102Updated 5 months ago
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆117Updated last year
- Publicly released code for the LAMBERT model☆101Updated 3 years ago
- CTE: Contextualized Table Extraction Dataset☆17Updated last year
- ☆31Updated 10 months ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆134Updated last year
- ☆57Updated 3 years ago
- Official implementation for Dessurt☆58Updated 2 years ago
- OCR Annotations from Amazon Textract for Industry Documents Library☆101Updated 2 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆122Updated 9 months ago
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆50Updated 2 years ago
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆175Updated 2 months ago
- ☆42Updated 2 years ago
- An unofficial Pytorch implementation of ERNIE-Layout which is originally released through PaddleNLP.☆104Updated last year
- InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)☆159Updated 8 months ago
- Streamlit Named Entity Recognition (NER) annotation custom component☆39Updated 2 years ago
- ☆38Updated 3 years ago
- The WordScape repository contains code for the WordScape pipeline to create datasets to train document understanding models.☆33Updated last year
- Incorporating VIsual LAyout Structures for Scientific Text Classification☆175Updated last year
- ☆60Updated last year
- An unofficial Implementation of DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents☆36Updated last year
- ☆157Updated 2 years ago
- Dataset and scripts for HRDoc☆35Updated last year
- Contrast-guided Feature Adjustment Module for Visual Information Extraction☆28Updated last year
- multimodal document analysis☆162Updated 8 months ago
- ☆50Updated 8 months ago
- ☆77Updated 2 years ago
- an unofficial code for augment-XY-CUT in XYLayoutLM☆28Updated 2 years ago
- Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task…☆267Updated 2 years ago