{"total":21,"rows":[{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180,"area":null},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143,"area":null},{"id":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106,"area":null},{"id":"2405.14295","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","created":"2024-05-23","cited_by_count":62,"area":null},{"id":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2303.17870","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","created":"2023-03-31","cited_by_count":34,"area":null},{"id":"2210.05391","title":"PP-StructureV2: A Stronger Document Analysis System","created":"2022-10-11","cited_by_count":20,"area":null},{"id":"2304.12484","title":"DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents","created":"2023-04-24","cited_by_count":19,"area":null},{"id":"2305.05886","title":"Computational Optics for Mobile Terminals in Mass Production","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2311.07306","title":"What Large Language Models Bring to Text-rich VQA?","created":"2023-11-13","cited_by_count":10,"area":null},{"id":"2404.04624","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","created":"2024-04-06","cited_by_count":9,"area":null},{"id":"2410.15359","title":"Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations","created":"2024-10-20","cited_by_count":8,"area":null},{"id":"2203.03819","title":"Table Structure Recognition with Conditional Attention","created":"2022-03-08","cited_by_count":6,"area":null},{"id":"2404.10305","title":"TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content","created":"2024-04-16","cited_by_count":5,"area":null},{"id":"2501.07334","title":"Anonymization of Documents for Law Enforcement with Machine Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2211.02128","title":"Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognition","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2606.29905","title":"StrucTab: A Structured Optimization Framework for Table Parsing","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2208.12505","title":"AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications","created":"2022-08-26","cited_by_count":1,"area":null},{"id":"2301.06680","title":"DIGITOUR: Automatic Digital Tours for Real-Estate Properties","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2407.16076","title":"PLayerTV: Advanced Player Tracking and Identification for Automatic Soccer Highlight Clips","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2410.05096","title":"Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llava","created":"2024-10-07","cited_by_count":0,"area":null}],"next_cursor":null}