{"total":17,"rows":[{"id":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"area":null},{"id":"2208.11168","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","created":"2022-08-23","cited_by_count":17,"area":null},{"id":"2401.11874","title":"Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis","created":"2024-01-22","cited_by_count":15,"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":"2405.11757","title":"DLAFormer: An End-to-End Transformer For Document Layout Analysis","created":"2024-05-20","cited_by_count":11,"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":"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":"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":"2405.03104","title":"GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2209.10441","title":"A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2401.09232","title":"Dynamic Relation Transformer for Contextual Text Block Detection","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2406.08610","title":"LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2512.20236","title":"IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2503.16664","title":"TextBite: A Historical Czech Document Dataset for Logical Page Segmentation","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2508.06988","title":"TADoc: Robust Time-Aware Document Image Dewarping","created":"2025-08-09","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}],"next_cursor":null}