chenxn2020 / GOSELinks
[Paper] Code for the EMNLP2023 (Findings) paper "Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document"
☆17Updated 2 years ago
Alternatives and similar repositories for GOSE
Users that are interested in GOSE are comparing it to the libraries listed below
Sorting:
- ICDAR 2024 Table OCR Model☆39Updated last week
- ☆14Updated last year
- Code for ICCV 2023 Paper : “ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction”☆54Updated 2 years ago
- Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)☆126Updated 2 years ago
- ☆108Updated 4 years ago
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆52Updated 3 years ago
- chinese document classification of layoutlmv3 and layoutxlm☆46Updated 3 years ago
- WikiTableSet: A largest publicly available image-based table recognition dataset in three languages built from Wikipedia☆32Updated 8 months ago
- CTE: Contextualized Table Extraction Dataset☆17Updated 2 years ago
- Contrast-guided Feature Adjustment Module for Visual Information Extraction☆30Updated 2 years ago
- ☆97Updated 3 years ago
- ☆57Updated 2 years ago
- An unofficial Pytorch implementation of ERNIE-Layout which is originally released through PaddleNLP.☆107Updated 2 years ago
- Table Structure Recognition☆81Updated 2 years ago
- ☆102Updated last year
- XFUND: A Multilingual Form Understanding Benchmark☆217Updated 3 years ago
- ☆157Updated 9 months ago
- Searching a High Performance Feature Extractor for Text Recognition Network. TPAMI 2022☆13Updated 3 years ago
- 1st Solution For ICDAR 2021 Competition on Mathematical Formula Detection(公式检测冠军方案)☆133Updated 2 years ago
- Dataset and scripts for HRDoc☆41Updated 2 years ago
- Tool to parse wiki tables from the HTML dump of Wikipedia☆11Updated 3 years ago
- An official implementation of paper "Paragraph2Graph: A Language-independent GNN-based framework for layout analysis"☆81Updated 2 years ago
- Datasets and Evaluation Scripts for CompHRDoc☆55Updated 11 months ago
- ☆40Updated last year
- ☆51Updated last year
- SPRINT: Script-agnostic Structure Recognition in Tables☆16Updated 10 months ago
- Read Ten Lines at One Glance: Line-Aware Semi-Autoregressive Transformer for Multi-Line Handwritten Mathematical Expression Recognition☆28Updated 2 years ago
- [AAAI 2025] DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming☆36Updated 8 months ago
- Official implementation of URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding (AAAI 2026…☆34Updated last week
- GCN use for semi-construct document information extraction.☆21Updated 2 years ago