{"total":33,"rows":[{"id":"2202.13669","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","created":"2022-02-28","cited_by_count":107,"area":null},{"id":"2108.11591","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","created":"2021-08-26","cited_by_count":80,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2105.06220","title":"VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations","created":"2021-05-13","cited_by_count":40,"area":null},{"id":"2106.00676","title":"VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups","created":"2021-06-01","cited_by_count":27,"area":null},{"id":"2303.14884","title":"A large-scale dataset for end-to-end table recognition in the wild","created":"2023-03-27","cited_by_count":24,"area":null},{"id":"2104.14272","title":"Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks","created":"2021-04-29","cited_by_count":18,"area":null},{"id":"2107.04419","title":"Form2Seq : A Framework for Higher-Order Form Structure Extraction","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2105.06400","title":"TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables","created":"2021-05-12","cited_by_count":15,"area":null},{"id":"2211.08469","title":"Deep learning for table detection and structure recognition: A survey","created":"2022-11-15","cited_by_count":15,"area":null},{"id":"2106.15322","title":"TNCR: Table Net Detection and Classification Dataset","created":"2021-06-19","cited_by_count":14,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2301.12293","title":"ACL-Fig: A Dataset for Scientific Figure Classification","created":"2023-01-28","cited_by_count":10,"area":null},{"id":"2102.09395","title":"Robust PDF Document Conversion Using Recurrent Neural Networks","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2105.14426","title":"ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX","created":"2021-05-30","cited_by_count":9,"area":null},{"id":"2108.12961","title":"BioFors: A Large Biomedical Image Forensics Dataset","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2206.00785","title":"Delivering Document Conversion as a Cloud Service with High Throughput and Responsiveness","created":"2022-06-01","cited_by_count":7,"area":null},{"id":"2210.17246","title":"Tables to LaTeX: structure and content extraction from scientific tables","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2107.04396","title":"Multi-Modal Association based Grouping for Form Structure Extraction","created":"2021-07-09","cited_by_count":6,"area":null},{"id":"2107.13306","title":"Tab2Know: Building a Knowledge Base from Tables in Scientific Papers","created":"2021-07-28","cited_by_count":5,"area":null},{"id":"2307.02065","title":"Line Graphics Digitization: A Step Towards Full Automation","created":"2023-07-05","cited_by_count":5,"area":null},{"id":"2209.09207","title":"Table Detection in the Wild: A Novel Diverse Table Detection Dataset and Method","created":"2022-08-31","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":"2106.07359","title":"MexPub: Deep Transfer Learning for Metadata Extraction from German Publications","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2106.15320","title":"ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and Dissertations","created":"2021-06-23","cited_by_count":2,"area":null},{"id":"2105.14931","title":"Document Domain Randomization for Deep Learning Document Layout Extraction","created":"2021-05-20","cited_by_count":1,"area":null},{"id":"2305.04460","title":"Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2305.17401","title":"A Framework For Refining Text Classification and Object Recognition from Academic Articles","created":"2023-05-27","cited_by_count":1,"area":null},{"id":"2312.09038","title":"Object Recognition from Scientific Document based on Compartment Refinement Framework","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2311.04711","title":"Training CLIP models on Data from Scientific Papers","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2312.11146","title":"OsmLocator: locating overlapping scatter marks with a non-training generative perspective","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2607.23886","title":"Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.22214","title":"Query-Driven Multimodal Information Extraction from Long Documents","created":"2026-08-23","cited_by_count":0,"area":null}],"next_cursor":null}