{"total":88,"rows":[{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117,"area":null},{"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":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91,"area":null},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90,"area":null},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82,"area":null},{"id":"2203.06947","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","created":"2022-03-14","cited_by_count":68,"area":null},{"id":"2210.06155","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","created":"2022-10-12","cited_by_count":67,"area":null},{"id":"2102.06732","title":"Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution","created":"2021-01-24","cited_by_count":64,"area":null},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64,"area":null},{"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":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2305.07498","title":"Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution","created":"2023-05-12","cited_by_count":54,"area":null},{"id":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"id":"2103.14470","title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","created":"2021-03-26","cited_by_count":43,"area":null},{"id":"2108.06543","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","created":"2021-08-14","cited_by_count":40,"area":null},{"id":"2105.11672","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","created":"2021-05-25","cited_by_count":29,"area":null},{"id":"2306.00526","title":"Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering","created":"2023-06-01","cited_by_count":24,"area":null},{"id":"2106.10786","title":"ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction","created":"2021-06-21","cited_by_count":22,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2305.02549","title":"FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction","created":"2023-05-04","cited_by_count":20,"area":null},{"id":"2304.12484","title":"DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents","created":"2023-04-24","cited_by_count":19,"area":null},{"id":"2106.12940","title":"MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction","created":"2021-06-24","cited_by_count":18,"area":null},{"id":"2307.07929","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2309.01131","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","created":"2023-09-03","cited_by_count":18,"area":null},{"id":"2305.18721","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","created":"2023-05-30","cited_by_count":17,"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":"2104.08405","title":"LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2104.08041","title":"Cost-effective End-to-end Information Extraction for Semi-structured Document Images","created":"2021-04-16","cited_by_count":14,"area":null},{"id":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2209.08569","title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding","created":"2022-09-18","cited_by_count":9,"area":null},{"id":"2505.13535","title":"Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2106.10681","title":"Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences","created":"2021-06-20","cited_by_count":8,"area":null},{"id":"2310.16131","title":"GenKIE: Robust Generative Multimodal Document Key Information Extraction","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2507.09861","title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","created":"2025-07-14","cited_by_count":8,"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":"2106.14624","title":"Key Information Extraction From Documents: Evaluation And Generator","created":"2021-06-09","cited_by_count":7,"area":null},{"id":"2109.01078","title":"Skim-Attention: Learning to Focus via Document Layout","created":"2021-09-02","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":"2211.07730","title":"QueryForm: A Simple Zero-shot Form Entity Query Framework","created":"2022-11-14","cited_by_count":7,"area":null},{"id":"2501.06659","title":"Visual Template Inference for Data Extraction from Documents","created":"2025-01-11","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":"2207.04713","title":"GMN: Generative Multi-modal Network for Practical Document Information Extraction","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2308.07777","title":"Enhancing Visually-Rich Document Understanding via Layout Structure Modeling","created":"2023-08-15","cited_by_count":6,"area":null},{"id":"2408.06345","title":"Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2108.10395","title":"Using Neighborhood Context to Improve Information Extraction from Visual Documents Captured on Mobile Phones","created":"2021-08-23","cited_by_count":5,"area":null},{"id":"2305.01938","title":"Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2405.17336","title":"XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser","created":"2024-05-27","cited_by_count":5,"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":"2105.04313","title":"DocReader: Bounding-Box Free Training of a Document Information Extraction Model","created":"2021-05-10","cited_by_count":4,"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":"2107.08128","title":"The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2110.04282","title":"Field Extraction from Forms with Unlabeled Data","created":"2021-10-08","cited_by_count":4,"area":null},{"id":"2103.05908","title":"DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction","created":"2021-03-10","cited_by_count":3,"area":null},{"id":"2109.00442","title":"Position Masking for Improved Layout-Aware Document Understanding","created":"2021-09-01","cited_by_count":3,"area":null},{"id":"2109.13967","title":"One-shot Key Information Extraction from Document with Deep Partial Graph Matching","created":"2021-09-26","cited_by_count":3,"area":null},{"id":"2309.05429","title":"Improving Information Extraction on Business Documents with Specific Pre-Training Tasks","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2409.11887","title":"DocMamba: Efficient Document Pre-training with State Space Model","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2111.04045","title":"Information Extraction from Visually Rich Documents with Font Style Embeddings","created":"2021-11-07","cited_by_count":2,"area":null},{"id":"2201.02647","title":"Data-Efficient Information Extraction from Form-Like Documents","created":"2022-01-07","cited_by_count":2,"area":null},{"id":"2207.13979","title":"Knowing Where and What: Unified Word Block Pretraining for Document Understanding","created":"2022-07-28","cited_by_count":2,"area":null},{"id":"2309.05503","title":"Long-Range Transformer Architectures for Document Understanding","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2310.03777","title":"PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2410.01160","title":"GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2510.02133","title":"FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2110.04413","title":"Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2206.06890","title":"RDU: A Region-based Approach to Form-style Document Understanding","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2207.06695","title":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","created":"2022-07-14","cited_by_count":1,"area":null},{"id":"2301.12394","title":"DocILE 2023 Teaser: Document Information Localization and Extraction","created":"2023-01-29","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":"2306.00750","title":"End-to-End Document Classification and Key Information Extraction using Assignment Optimization","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2310.14785","title":"Vision-Enhanced Semantic Entity Recognition in Document Images via Visually-Asymmetric Consistency Learning","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2112.12353","title":"LAME: Layout Aware Metadata Extraction Approach for Research Articles","created":"2021-12-23","cited_by_count":0,"area":null},{"id":"2305.14218","title":"DUBLIN -- Document Understanding By Language-Image Network","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2403.15765","title":"Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2404.00488","title":"Noise-Aware Training of Layout-Aware Language Models","created":"2024-03-30","cited_by_count":0,"area":null},{"id":"2407.06826","title":"VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2409.15004","title":"ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2412.10155","title":"WordVIS: A Color Worth A Thousand Words","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2510.15727","title":"Invoice Information Extraction: Methods and Performance Evaluation","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.05547","title":"Automated Invoice Data Extraction: Using LLM and OCR","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2603.28028","title":"Efficient Domain Adaptation for Text Line Recognition via Decoupled Language Models","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2609.17538","title":"From Pixels to Pairs: A Comprehensive Benchmark of LLM-Driven Key-Value Extraction in Noisy Document Settings","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.31341","title":"The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}