{"total":22,"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Image Analysis","created":"2021-03-29","cited_by_count":58,"area":null},{"id":"2203.08504","title":"A Survey of Historical Document Image Datasets","created":"2022-03-16","cited_by_count":20,"area":null},{"id":"2201.11438","title":"DocSegTr: An Instance-Level End-to-End Document Image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":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","cited_by_count":13,"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":"2305.00795","title":"SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2103.09354","title":"Digital Peter: Dataset, Competition and Handwriting Recognition Methods","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2310.10050","title":"EfficientOCR: An Extensible, Open-Source Package for Efficiently Digitizing World Knowledge","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2202.08125","title":"Processing the structure of documents: Logical Layout Analysis of historical newspapers in French","created":"2022-02-16","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2305.14588","title":"Evaluating end-to-end entity linking on domain-specific knowledge bases: Learning about ancient technologies from museum collections","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2406.06236","title":"UnSupDLA: Towards Unsupervised Document Layout Analysis","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2201.09407","title":"Cross-Domain Document Layout Analysis Using Document Style Guide","created":"2022-01-24","cited_by_count":1,"area":null},{"id":"2504.08645","title":"Title block detection and information extraction for enhanced building drawings search","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2111.13809","title":"Document Layout Analysis with Aesthetic-Guided Image Augmentation","created":"2021-11-27","cited_by_count":0,"area":null},{"id":"2112.13850","title":"Using maps to predict economic activity","created":"2021-12-27","cited_by_count":0,"area":null},{"id":"2511.19919","title":"HybriDLA: Hybrid Generation for Document Layout Analysis","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2605.25781","title":"Double Triangle Annotation: A Scalable Human-in-the-Loop Framework for High-Precision Historical Document Annotation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.17355","title":"Complex Layout Classification in the Wild: A Low-Resource Approach with Layout-Preserving Augmentations","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2609.31651","title":"PalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}