{"total":132,"rows":[{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116,"area":null},{"id":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"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":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"id":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39,"area":null},{"id":"2303.05063","title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","created":"2023-03-09","cited_by_count":38,"area":null},{"id":"2402.12365","title":"Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators","created":"2024-02-19","cited_by_count":27,"area":null},{"id":"2503.17213","title":"PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction","created":"2025-03-21","cited_by_count":26,"area":null},{"id":"2403.14252","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","created":"2024-03-21","cited_by_count":24,"area":null},{"id":"2310.11016","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","created":"2023-10-17","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":"2212.09621","title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","created":"2022-12-19","cited_by_count":20,"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":"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":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16,"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":"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":"2407.19787","title":"SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters","created":"2024-07-29","cited_by_count":14,"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":"2210.02849","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","created":"2022-10-06","cited_by_count":12,"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":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2308.02051","title":"A Graphical Approach to Document Layout Analysis","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2404.19024","title":"Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism","created":"2024-04-29","cited_by_count":8,"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":"2305.00795","title":"SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation","created":"2023-05-01","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":"2310.09118","title":"DSG: An End-to-End Document Structure Generator","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2312.10188","title":"WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2408.15646","title":"{\\mu}gat: Improving Single-Page Document Parsing by Providing Multi-Page Context","created":"2024-08-28","cited_by_count":7,"area":null},{"id":"2305.14962","title":"ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2306.02623","title":"Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2403.04080","title":"Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis","created":"2024-03-06","cited_by_count":6,"area":null},{"id":"2404.17888","title":"A Hybrid Approach for Document Layout Analysis in Document images","created":"2024-04-27","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":"2304.06009","title":"Literature Review: Computer Vision Applications in Transportation Logistics and Warehousing","created":"2023-04-12","cited_by_count":5,"area":null},{"id":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2310.18343","title":"PHD: Pixel-Based Language Modeling of Historical Documents","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2408.11981","title":"Large Language Models for Page Stream Segmentation","created":"2024-08-21","cited_by_count":5,"area":null},{"id":"2511.14259","title":"ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation","created":"2025-11-18","cited_by_count":5,"area":null},{"id":"2512.20174","title":"Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2210.01959","title":"Detect, Retrieve, Comprehend: A Flexible Framework for Zero-Shot Document-Level Question Answering","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2306.08937","title":"DocumentNet: Bridging the Data Gap in Document Pre-Training","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2311.05565","title":"High-Performance Transformers for Table Structure Recognition Need Early Convolutions","created":"2023-11-09","cited_by_count":4,"area":null},{"id":"2402.18262","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2501.02235","title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","created":"2025-01-04","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":"2509.16506","title":"CommonForms: A Large, Diverse Dataset for Form Field Detection","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2511.22490","title":"SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts","created":"2025-11-27","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":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2303.03127","title":"ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents","created":"2023-03-06","cited_by_count":3,"area":null},{"id":"2309.12382","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2310.16356","title":"A Multi-Modal Multilingual Benchmark for Document Image Classification","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2310.18983","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2409.14128","title":"Present and Future Generalization of Synthetic Image Detectors","created":"2024-09-21","cited_by_count":3,"area":null},{"id":"2502.14901","title":"Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2503.15893","title":"UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2506.12116","title":"Unsupervised Document and Template Clustering using Multimodal Embeddings","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2507.23295","title":"LED Benchmark: Diagnosing Structural Layout Errors for Document Layout Analysis","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2604.10127","title":"VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2304.11810","title":"PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2305.10448","title":"Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding","created":"2023-05-16","cited_by_count":2,"area":null},{"id":"2307.09047","title":"Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2307.11845","title":"Multimodal Document Analytics for Banking Process Automation","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2311.18481","title":"ESG Accountability Made Easy: DocQA at Your Service","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2401.04746","title":"Skin Cancer Segmentation and Classification Using Vision Transformer for Automatic Analysis in Dermatoscopy-based Non-invasive Digital System","created":"2024-01-09","cited_by_count":2,"area":null},{"id":"2405.00420","title":"Self-supervised Pre-training of Text Recognizers","created":"2024-05-01","cited_by_count":2,"area":null},{"id":"2411.03730","title":"NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2503.18742","title":"SFDLA: Source-Free Document Layout Analysis","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2506.01388","title":"VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding","created":"2025-06-02","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":"2601.14490","title":"GutenOCR: A Grounded Vision-Language Front-End for Documents","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2606.23344","title":"RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2204.05486","title":"Neural Graph Matching for Modification Similarity Applied to Electronic Document Comparison","created":"2022-04-12","cited_by_count":1,"area":null},{"id":"2208.10180","title":"TaCo: Textual Attribute Recognition via Contrastive Learning","created":"2022-08-22","cited_by_count":1,"area":null},{"id":"2211.01165","title":"RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild","created":"2022-11-02","cited_by_count":1,"area":null},{"id":"2211.14777","title":"Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models","created":"2022-11-27","cited_by_count":1,"area":null},{"id":"2301.11316","title":"Open Problems in Applied Deep Learning","created":"2023-01-26","cited_by_count":1,"area":null},{"id":"2305.17219","title":"GVdoc: Graph-based Visual Document Classification","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2310.00917","title":"Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance","created":"2023-10-02","cited_by_count":1,"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":"2402.14579","title":"Text Role Classification in Scientific Charts Using Multimodal Transformers","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.17664","title":"DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2408.01038","title":"UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2409.00909","title":"ViRED: Prediction of Visual Relations in Engineering Drawings","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2410.01166","title":"Document Classification using File Names","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2502.19202","title":"LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2503.19658","title":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2507.08865","title":"Spatial ModernBERT: Spatial-Aware Transformer for Table and Key-Value Extraction in Financial Documents at Scale","created":"2025-07-09","cited_by_count":1,"area":null}],"next_cursor":"100"}