{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485},{"id":"2004.02349","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","created":"2020-04-05","cited_by_count":434},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"1812.09449","title":"A Survey on Deep Learning for Named Entity Recognition","created":"2018-12-22","cited_by_count":282},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","cited_by_count":214},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2009.09941","title":"PP-OCR: A Practical Ultra Lightweight OCR System","created":"2020-09-21","cited_by_count":151},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"2005.00589","title":"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context","created":"2020-05-01","cited_by_count":147},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"1907.00945","title":"ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019","created":"2019-07-01","cited_by_count":139},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134},{"id":"2110.00061","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","created":"2021-09-30","cited_by_count":126},{"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},{"id":"2108.04539","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","created":"2021-08-10","cited_by_count":104},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"id":"1809.08799","title":"Chargrid: Towards Understanding 2D Documents","created":"2018-09-24","cited_by_count":100},{"id":"2203.01017","title":"TableFormer: Table Structure Understanding with Transformers","created":"2022-03-02","cited_by_count":94},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2203.06947","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","created":"2022-03-14","cited_by_count":68},{"id":"2005.00642","title":"Spatial Dependency Parsing for Semi-Structured Document Information Extraction","created":"2020-05-01","cited_by_count":65},{"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},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64},{"id":"1909.04948","title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","created":"2019-09-11","cited_by_count":63},{"id":"2001.00139","title":"Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)","created":"2020-01-01","cited_by_count":56},{"id":"2002.08087","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","created":"2020-02-19","cited_by_count":53},{"id":"2103.14470","title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","created":"2021-03-26","cited_by_count":43},{"id":"1804.02445","title":"Extracting Scientific Figures with Distantly Supervised Neural Networks","created":"2018-04-06","cited_by_count":36},{"id":"2202.12985","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","created":"2022-02-25","cited_by_count":35},{"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},{"id":"1812.07248","title":"Attend, Copy, Parse -- End-to-end information extraction from documents","created":"2018-12-18","cited_by_count":25},{"id":"1909.02576","title":"Deep Visual Template-Free Form Parsing","created":"2019-09-05","cited_by_count":24},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24},{"id":"1710.05703","title":"A Survey on Optical Character Recognition System","created":"2017-10-03","cited_by_count":23},{"id":"1801.09919","title":"E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text","created":"2018-01-30","cited_by_count":21},{"id":"1903.12363","title":"CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor","created":"2019-03-29","cited_by_count":21},{"id":"2009.14457","title":"Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning","created":"2020-09-30","cited_by_count":21},{"id":"2006.16405","title":"Unsupervised Calibration under Covariate Shift","created":"2020-06-29","cited_by_count":15},{"id":"2106.11695","title":"The Hitchhiker's Guide to Prior-Shift Adaptation","created":"2021-06-22","cited_by_count":13},{"id":"1904.12577","title":"Table understanding in structured documents","created":"2019-03-22","cited_by_count":11},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11},{"id":"2006.06244","title":"CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks","created":"2020-06-11","cited_by_count":10},{"id":"2104.10355","title":"Revisiting Document Representations for Large-Scale Zero-Shot Learning","created":"2021-04-21","cited_by_count":9},{"id":"1906.02427","title":"One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis","created":"2019-06-06","cited_by_count":8},{"id":"2106.14624","title":"Key Information Extraction From Documents: Evaluation And Generator","created":"2021-06-09","cited_by_count":7},{"id":"1910.10037","title":"One-Shot Template Matching for Automatic Document Data Capture","created":"2019-10-22","cited_by_count":5},{"id":"2210.07903","title":"Text Detection Forgot About Document OCR","created":"2022-10-14","cited_by_count":5},{"id":"2301.12394","title":"DocILE 2023 Teaser: Document Information Localization and Extraction","created":"2023-01-29","cited_by_count":1}],"next_cursor":null}