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.
☆76Updated last year
Alternatives and similar repositories for vrdu:
Users that are interested in vrdu are comparing it to the libraries listed below
- ReadingBank: A Benchmark Dataset for Reading Order Detection☆96Updated 4 months ago
- ☆55Updated 3 years ago
- The code related to the baselines from NeurIPS 2021 paper "DUE: End-to-End Document Understanding Benchmark."☆36Updated last year
- Official implementation for Dessurt☆57Updated 2 years ago
- Publicly released code for the LAMBERT model☆101Updated 3 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆120Updated 8 months ago
- ☆157Updated 2 years ago
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆117Updated last year
- An unofficial Implementation of DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents☆36Updated last year
- multimodal document analysis☆161Updated 7 months ago
- ☆58Updated last year
- My implementation of Kosmos2.5 from the paper: "KOSMOS-2.5: A Multimodal Literate Model"☆70Updated 2 months ago
- OCR Annotations from Amazon Textract for Industry Documents Library☆101Updated 2 years ago
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆173Updated last month
- The WordScape repository contains code for the WordScape pipeline to create datasets to train document understanding models.☆33Updated last year
- Contrast-guided Feature Adjustment Module for Visual Information Extraction☆28Updated last year
- CTE: Contextualized Table Extraction Dataset☆17Updated last year
- ☆31Updated 9 months ago
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆49Updated 2 years ago
- ☆50Updated 7 months ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆132Updated last year
- ☆23Updated 3 years ago
- ☆42Updated 2 years ago
- Document Visual Question Answering☆112Updated 4 years ago
- Incorporating VIsual LAyout Structures for Scientific Text Classification☆174Updated last year
- an unofficial code for augment-XY-CUT in XYLayoutLM☆28Updated 2 years ago
- ☆37Updated 3 years ago
- An unofficial Pytorch implementation of ERNIE-Layout which is originally released through PaddleNLP.☆101Updated last year
- DocLLM: A layout-aware generative language model for multimodal document understanding☆119Updated last year
- Dataset and scripts for HRDoc☆34Updated last year