{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"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":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"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":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106},{"id":"1809.08799","title":"Chargrid: Towards Understanding 2D Documents","created":"2018-09-24","cited_by_count":100},{"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":"1903.11279","title":"Graph Convolution for Multimodal Information Extraction from Visually Rich Documents","created":"2019-03-27","cited_by_count":88},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"id":"2210.06155","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","created":"2022-10-12","cited_by_count":67},{"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":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62},{"id":"2005.13118","title":"TRIE: End-to-End Text Reading and Information Extraction for Document Understanding","created":"2020-05-27","cited_by_count":61},{"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},{"id":"2309.10952","title":"LMDX: Language Model-based Document Information Extraction and Localization","created":"2023-09-19","cited_by_count":37},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37},{"id":"2211.15421","title":"VRDU: A Benchmark for Visually-rich Document Understanding","created":"2022-11-15","cited_by_count":35},{"id":"2109.07460","title":"Efficient Domain Adaptation of Language Models via Adaptive Tokenization","created":"2021-09-15","cited_by_count":34},{"id":"1708.07403","title":"CloudScan - A configuration-free invoice analysis system using recurrent neural networks","created":"2017-08-24","cited_by_count":33},{"id":"2011.13534","title":"A Survey of Deep Learning Approaches for OCR and Document Understanding","created":"2020-11-27","cited_by_count":32},{"id":"2010.11685","title":"DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding","created":"2020-10-15","cited_by_count":31},{"id":"1812.07248","title":"Attend, Copy, Parse -- End-to-end information extraction from documents","created":"2018-12-18","cited_by_count":25},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24},{"id":"2403.14252","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","created":"2024-03-21","cited_by_count":24},{"id":"2110.09915","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","created":"2021-10-19","cited_by_count":23},{"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},{"id":"2304.12484","title":"DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents","created":"2023-04-24","cited_by_count":19},{"id":"2307.07929","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","created":"2023-07-16","cited_by_count":18},{"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},{"id":"2009.04153","title":"One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information Extraction","created":"2020-09-09","cited_by_count":16},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11},{"id":"2010.02358","title":"VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach","created":"2020-10-05","cited_by_count":10},{"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},{"id":"2106.00978","title":"A Span Extraction Approach for Information Extraction on Visually-Rich Documents","created":"2021-06-02","cited_by_count":6},{"id":"2207.04713","title":"GMN: Generative Multi-modal Network for Practical Document Information Extraction","created":"2022-07-11","cited_by_count":6},{"id":"2303.15100","title":"An Information Extraction Study: Take In Mind the Tokenization!","created":"2023-03-27","cited_by_count":6},{"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},{"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},{"id":"2105.04313","title":"DocReader: Bounding-Box Free Training of a Document Information Extraction Model","created":"2021-05-10","cited_by_count":4},{"id":"2304.14936","title":"Information Redundancy and Biases in Public Document Information Extraction Benchmarks","created":"2023-04-28","cited_by_count":4},{"id":"2009.14040","title":"Modelling service-oriented systems and cloud services with Heraklit","created":"2020-09-29","cited_by_count":3},{"id":"2309.05429","title":"Improving Information Extraction on Business Documents with Specific Pre-Training Tasks","created":"2023-09-11","cited_by_count":3},{"id":"2405.03104","title":"GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding","created":"2024-05-06","cited_by_count":3},{"id":"2111.04045","title":"Information Extraction from Visually Rich Documents with Font Style Embeddings","created":"2021-11-07","cited_by_count":2},{"id":"2401.03472","title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","created":"2024-01-07","cited_by_count":2},{"id":"2403.18183","title":"Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence","created":"2024-03-27","cited_by_count":2},{"id":"2404.18664","title":"Reading Order Independent Metrics for Information Extraction in Handwritten Documents","created":"2024-04-29","cited_by_count":2},{"id":"2210.03453","title":"Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections","created":"2022-10-07","cited_by_count":1},{"id":"2301.10781","title":"Generalizability in Document Layout Analysis for Scientific Article Figure & Caption Extraction","created":"2023-01-25","cited_by_count":1}],"next_cursor":null}