Table Transformer Structure Recognition V1.1 All
A Transformer-based model for table structure recognition, designed to detect table structures in documents
Downloads 395.03k
Release Time : 11/18/2023
Model Overview
This model is based on the DETR architecture, specifically designed for recognizing table structures in documents, supporting the extraction of table information from complex documents
Model Features
Transformer-Based Table Detection
Utilizes the DETR architecture to effectively recognize table structures in documents
Pre-trained Model
Pre-trained on the PubTables1M and FinTabNet.c datasets
Pre-Normalization Setup
Applies layer normalization before self-attention and cross-attention to enhance model stability
Model Capabilities
Document Table Detection
Table Structure Recognition
Document Information Extraction
Use Cases
Document Processing
Financial Document Analysis
Extract table data from financial statements
Accurately identifies complex financial table structures
Academic Paper Processing
Extract research data tables from academic papers
Handles various formats of academic tables
Enterprise Document Management
Contract Document Parsing
Automatically identify price and clause tables in contracts
Improves contract processing efficiency
Featured Recommended AI Models