{"total":90,"rows":[{"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":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97,"area":null},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91,"area":null},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88,"area":null},{"id":"2203.02177","title":"GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation","created":"2022-03-04","cited_by_count":87,"area":null},{"id":"2410.12628","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","created":"2024-10-16","cited_by_count":82,"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":"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":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46,"area":null},{"id":"2107.05214","title":"Split, embed and merge: An accurate table structure recognizer","created":"2021-07-12","cited_by_count":42,"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":"2202.00217","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","created":"2022-02-01","cited_by_count":34,"area":null},{"id":"2203.09056","title":"Robust Table Detection and Structure Recognition from Heterogeneous Document Images","created":"2022-03-17","cited_by_count":30,"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":"2110.12826","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","created":"2021-10-25","cited_by_count":26,"area":null},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24,"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":"2409.08573","title":"HTR-VT: Handwritten Text Recognition with Vision Transformer","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23,"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":"2102.11838","title":"Page Layout Analysis System for Unconstrained Historic Documents","created":"2021-02-23","cited_by_count":20,"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":"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":"2101.12741","title":"Post-OCR Paragraph Recognition by Graph Convolutional Networks","created":"2021-01-29","cited_by_count":16,"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":"2105.08194","title":"Visual FUDGE: Form Understanding via Dynamic Graph Editing","created":"2021-05-17","cited_by_count":15,"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":"2205.12029","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification","created":"2022-05-24","cited_by_count":14,"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":"2205.12840","title":"SALAD: Source-free Active Label-Agnostic Domain Adaptation for Classification, Segmentation and Detection","created":"2022-05-24","cited_by_count":10,"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":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","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":"2203.09638","title":"Unified Line and Paragraph Detection by Graph Convolutional Networks","created":"2022-03-17","cited_by_count":7,"area":null},{"id":"2212.13924","title":"Page Layout Analysis of Text-heavy Historical Documents: a Comparison of Textual and Visual Approaches","created":"2022-12-12","cited_by_count":7,"area":null},{"id":"2305.02769","title":"Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2306.13526","title":"Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images","created":"2023-06-23","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":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2305.00630","title":"TRACE: Table Reconstruction Aligned to Corner and Edges","created":"2023-05-01","cited_by_count":6,"area":null},{"id":"2106.07615","title":"Magic Layouts: Structural Prior for Component Detection in User Interface Designs","created":"2021-06-14","cited_by_count":5,"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":"2111.06016","title":"Synthetic Document Generator for Annotation-free Layout Recognition","created":"2021-11-11","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":"2405.00187","title":"Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2104.02874","title":"Document Layout Analysis via Dynamic Residual Feature Fusion","created":"2021-04-07","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":"2107.04357","title":"Graph-based Deep Generative Modelling for Document Layout Generation","created":"2021-07-09","cited_by_count":4,"area":null},{"id":"2108.13297","title":"VTLayout: Fusion of Visual and Text Features for Document Layout Analysis","created":"2021-08-12","cited_by_count":4,"area":null},{"id":"2203.12346","title":"Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2305.06923","title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2405.04971","title":"End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents","created":"2024-05-08","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":"2106.13802","title":"Efficient Document Image Classification Using Region-Based Graph Neural Network","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2306.05749","title":"DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures","created":"2023-06-09","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":"2108.02095","title":"Human-In-The-Loop Document Layout Analysis","created":"2021-08-04","cited_by_count":2,"area":null},{"id":"2205.08094","title":"MATrIX -- Modality-Aware Transformer for Information eXtraction","created":"2022-05-17","cited_by_count":2,"area":null},{"id":"2206.02628","title":"HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System","created":"2022-06-01","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":"2406.06236","title":"UnSupDLA: Towards Unsupervised Document Layout Analysis","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2406.08757","title":"SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2506.21055","title":"Class-Agnostic Region-of-Interest Matching in Document Images","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2507.05805","title":"DREAM: Document Reconstruction via End-to-end Autoregressive Model","created":"2025-07-08","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":"2510.26213","title":"OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2105.09297","title":"Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application","created":"2021-05-14","cited_by_count":1,"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":"2109.08477","title":"Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2112.12940","title":"Analyzing Scientific Publications using Domain-Specific Word Embedding and Topic Modelling","created":"2021-12-24","cited_by_count":1,"area":null},{"id":"2201.08574","title":"Classroom Slide Narration System","created":"2022-01-21","cited_by_count":1,"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":"2207.06695","title":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","created":"2022-07-14","cited_by_count":1,"area":null},{"id":"2302.08948","title":"Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories","created":"2023-02-17","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":"2102.02971","title":"Metaknowledge Extraction Based on Multi-Modal Documents","created":"2021-02-05","cited_by_count":0,"area":null},{"id":"2103.10139","title":"Learning Multimodal Affinities for Textual Editing in Images","created":"2021-03-18","cited_by_count":0,"area":null},{"id":"2108.09433","title":"BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation","created":"2021-08-21","cited_by_count":0,"area":null},{"id":"2110.08164","title":"Accurate Fine-grained Layout Analysis for the Historical Tibetan Document Based on the Instance Segmentation","created":"2021-10-15","cited_by_count":0,"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":"2209.06584","title":"One-Shot Doc Snippet Detection: Powering Search in Document Beyond Text","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2312.11043","title":"TDeLTA: A Light-weight and Robust Table Detection Method based on Learning Text Arrangement","created":"2023-12-18","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}],"next_cursor":null}