{"total":34,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45,"area":null},{"id":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40,"area":null},{"id":"2205.00146","title":"Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator","created":"2022-04-30","cited_by_count":32,"area":null},{"id":"2203.03382","title":"Self-supervised Implicit Glyph Attention for Text Recognition","created":"2022-03-07","cited_by_count":25,"area":null},{"id":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23,"area":null},{"id":"2504.21682","title":"Visual Text Processing: A Comprehensive Review and Unified Evaluation","created":"2025-04-30","cited_by_count":19,"area":null},{"id":"2602.20903","title":"TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering","created":"2026-02-24","cited_by_count":15,"area":null},{"id":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","cited_by_count":8,"area":null},{"id":"2402.03082","title":"Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2305.00795","title":"SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2209.02397","title":"A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data","created":"2022-09-06","cited_by_count":5,"area":null},{"id":"2211.03256","title":"On Web-based Visual Corpus Construction for Visual Document Understanding","created":"2022-11-07","cited_by_count":5,"area":null},{"id":"2403.10047","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2406.08354","title":"DocSynthv2: A Practical Autoregressive Modeling for Document Generation","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2306.12050","title":"Analyzing Font Style Usage and Contextual Factors in Real Images","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2405.00260","title":"CREPE: Coordinate-Aware End-to-End Document Parser","created":"2024-05-01","cited_by_count":3,"area":null},{"id":"2306.14269","title":"Weakly Supervised Scene Text Generation for Low-resource Languages","created":"2023-06-25","cited_by_count":2,"area":null},{"id":"2309.00410","title":"Selective Scene Text Removal","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2310.13366","title":"PSGText: Stroke-Guided Scene Text Editing with PSP Module","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2402.16356","title":"What Text Design Characterizes Book Genres?","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2406.06236","title":"UnSupDLA: Towards Unsupervised Document Layout Analysis","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2601.16113","title":"synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2602.06450","title":"What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2606.24484","title":"Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2208.06079","title":"Character decomposition to resolve class imbalance problem in Hangul OCR","created":"2022-08-12","cited_by_count":1,"area":null},{"id":"2506.17051","title":"Relaxed syntax modeling in Transformers for future-proof license plate recognition","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2605.12623","title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2308.10647","title":"bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2402.15236","title":"Font Impression Estimation in the Wild","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2409.17747","title":"Text Image Generation for Low-Resource Languages with Dual Translation Learning","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2505.18479","title":"Syn3DTxt: Embedding 3D Cues for Scene Text Generation","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2510.07951","title":"A Large-scale Dataset for Robust Complex Anime Scene Text Detection","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2607.00250","title":"LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}