{"total":31,"rows":[{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62,"area":null},{"id":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62,"area":null},{"id":"2103.15348","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","created":"2021-03-29","cited_by_count":58,"area":null},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46,"area":null},{"id":"2203.08504","title":"A Survey of Historical Document Image Datasets","created":"2022-03-16","cited_by_count":20,"area":null},{"id":"2102.08742","title":"SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition","created":"2021-02-17","cited_by_count":19,"area":null},{"id":"2201.11438","title":"DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer","created":"2022-01-27","cited_by_count":19,"area":null},{"id":"2305.04609","title":"SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation","created":"2023-05-08","cited_by_count":13,"area":null},{"id":"2301.10593","title":"Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition","created":"2023-01-25","cited_by_count":9,"area":null},{"id":"2106.00980","title":"End-to-End Hierarchical Relation Extraction for Generic Form Understanding","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2202.01414","title":"DocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts","created":"2022-02-03","cited_by_count":7,"area":null},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2106.00952","title":"End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Net","created":"2021-06-02","cited_by_count":4,"area":null},{"id":"2203.12346","title":"Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2304.14044","title":"Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records","created":"2023-04-27","cited_by_count":4,"area":null},{"id":"2404.18706","title":"The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censuses","created":"2024-04-29","cited_by_count":4,"area":null},{"id":"2210.15570","title":"Efficient few-shot learning for pixel-precise handwritten document layout analysis","created":"2022-10-27","cited_by_count":3,"area":null},{"id":"2507.08636","title":"Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificates","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2107.06777","title":"Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data","created":"2021-07-14","cited_by_count":2,"area":null},{"id":"2108.09436","title":"Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts","created":"2021-08-21","cited_by_count":2,"area":null},{"id":"2504.03621","title":"PILOT: A Promptable Interleaved Layout-aware OCR Transformer","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2101.07370","title":"Text line extraction using fully convolutional network and energy minimization","created":"2021-01-18","cited_by_count":1,"area":null},{"id":"2106.11797","title":"Evaluation of a Region Proposal Architecture for Multi-task Document Layout Analysis","created":"2021-06-22","cited_by_count":1,"area":null},{"id":"2109.08477","title":"Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2302.08948","title":"Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2308.11788","title":"An extensible point-based method for data chart value detection","created":"2023-08-22","cited_by_count":1,"area":null},{"id":"2110.02069","title":"OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis","created":"2021-10-01","cited_by_count":0,"area":null},{"id":"2312.04296","title":"Cross-codex Learning for Reliable Scribe Identification in Medieval Manuscripts","created":"2023-12-07","cited_by_count":0,"area":null},{"id":"2606.04166","title":"End-to-End Text Line Detection and Ordering","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.15886","title":"Text region detection in historical astronomical diagrams","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2608.18696","title":"Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts","created":"2026-08-19","cited_by_count":0,"area":null}],"next_cursor":null}