{"total":14,"rows":[{"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Image Analysis","created":"2021-03-29","cited_by_count":58,"area":null},{"id":"2203.08504","title":"A Survey of Historical Document Image Datasets","created":"2022-03-16","cited_by_count":20,"area":null},{"id":"2208.14558","title":"Augraphy: A Data Augmentation Library for Document Images","created":"2022-08-30","cited_by_count":14,"area":null},{"id":"2308.12477","title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers","created":"2023-08-24","cited_by_count":11,"area":null},{"id":"2304.02737","title":"Efficient OCR for Building a Diverse Digital History","created":"2023-04-05","cited_by_count":10,"area":null},{"id":"2403.17859","title":"ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2509.16506","title":"CommonForms: A Large, Diverse Dataset for Form Field Detection","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2603.25761","title":"A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2109.01732","title":"Navigating the Mise-en-Page: Interpretive Machine Learning Approaches to the Visual Layouts of Multi-Ethnic Periodicals","created":"2021-09-03","cited_by_count":1,"area":null},{"id":"2112.12703","title":"Digital Editions as Distant Supervision for Layout Analysis of Printed Books","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2509.13236","title":"Layout-Aware OCR for Black Digital Archives with Unsupervised Evaluation","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2206.10225","title":"Broken News: Making Newspapers Accessible to Print-Impaired","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2410.06314","title":"Temporal Image Caption Retrieval Competition -- Description and Results","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2610.13840","title":"Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}