DS3Lab / WordScapeLinks
The WordScape repository contains code for the WordScape pipeline to create datasets to train document understanding models.
☆37Updated last year
Alternatives and similar repositories for WordScape
Users that are interested in WordScape are comparing it to the libraries listed below
Sorting:
- Dataset and scripts for HRDoc☆38Updated 2 years ago
- Repository for the KVP10k dataset☆20Updated 2 weeks ago
- Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models, EMNLP 2023☆46Updated last year
- ☆67Updated last year
- OCR Annotations from Amazon Textract for Industry Documents Library☆103Updated 3 years ago
- ☆141Updated last year
- ☆153Updated 4 months ago
- Datasets and Evaluation Scripts for CompHRDoc☆50Updated 7 months ago
- ☆98Updated 9 months ago
- InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)☆159Updated last year
- CTE: Contextualized Table Extraction Dataset☆17Updated 2 years ago
- SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)☆96Updated 6 months ago
- Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)☆125Updated last year
- MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering. A comprehensive evaluation of multimodal large model multilingua…☆63Updated 4 months ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆151Updated 2 weeks ago
- ☆51Updated last year
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆52Updated 3 years ago
- My implementation of Kosmos2.5 from the paper: "KOSMOS-2.5: A Multimodal Literate Model"☆72Updated 3 weeks ago
- ☆44Updated last year
- ☆41Updated 8 months ago
- Dataset introduced in PlotQA: Reasoning over Scientific Plots☆79Updated 2 years ago
- Vary-tiny codebase upon LAVIS (for training from scratch)and a PDF image-text pairs data (about 600k including English/Chinese)☆86Updated last year
- An unofficial Pytorch implementation of ERNIE-Layout which is originally released through PaddleNLP.☆106Updated last year
- The code related to the baselines from NeurIPS 2021 paper "DUE: End-to-End Document Understanding Benchmark."☆36Updated 2 years ago
- We identify the desiderata for a comprehensive benchmark and propose Visually Rich Document Understanding (VRDU). VRDU contains two datas…☆80Updated 2 years ago
- ☆160Updated 2 years ago
- ReadingBank: A Benchmark Dataset for Reading Order Detection☆110Updated last year
- Official implementation for Dessurt: Document end-to-end self-supervised understanding and recognition transformer☆62Updated 2 years ago
- Official Implementation of TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism☆40Updated last month
- [AAAI 2025] DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming☆30Updated 4 months ago