{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"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":"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":"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":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"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":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"id":"1903.01949","title":"TableBank: A Benchmark Dataset for Table Detection and Recognition","created":"2019-03-05","cited_by_count":102},{"id":"1809.08799","title":"Chargrid: Towards Understanding 2D Documents","created":"2018-09-24","cited_by_count":100},{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100},{"id":"2004.12629","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","created":"2020-04-27","cited_by_count":98},{"id":"1706.02337","title":"Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network","created":"2017-06-07","cited_by_count":92},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"id":"1903.11279","title":"Graph Convolution for Multimodal Information Extraction from Visually Rich Documents","created":"2019-03-27","cited_by_count":88},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2108.11591","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","created":"2021-08-26","cited_by_count":80},{"id":"2004.07464","title":"PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks","created":"2020-04-16","cited_by_count":72},{"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":"1909.04948","title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","created":"2019-09-11","cited_by_count":63},{"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":"2002.08087","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","created":"2020-02-19","cited_by_count":53},{"id":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45},{"id":"1804.10371","title":"dhSegment: A generic deep-learning approach for document segmentation","created":"2018-04-27","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":"1909.09380","title":"EATEN: Entity-aware Attention for Single Shot Visual Text Extraction","created":"2019-09-20","cited_by_count":29},{"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":"1802.03345","title":"A Two-Stage Method for Text Line Detection in Historical Documents","created":"2018-02-09","cited_by_count":26},{"id":"1704.03557","title":"Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification","created":"2017-04-11","cited_by_count":22},{"id":"1801.09321","title":"Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks","created":"2018-01-29","cited_by_count":20},{"id":"2005.11017","title":"Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models","created":"2020-05-22","cited_by_count":20},{"id":"2008.02569","title":"IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documents","created":"2020-08-06","cited_by_count":16},{"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":"2106.14616","title":"ICDAR 2021 Competition on Scientific Literature Parsing","created":"2021-06-08","cited_by_count":16},{"id":"1912.04376","title":"Modular Multimodal Architecture for Document Classification","created":"2019-12-09","cited_by_count":15},{"id":"2104.08405","title":"LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding","created":"2021-04-16","cited_by_count":15},{"id":"2105.06400","title":"TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables","created":"2021-05-12","cited_by_count":15},{"id":"2106.15322","title":"TNCR: Table Net Detection and Classification Dataset","created":"2021-06-19","cited_by_count":14},{"id":"1708.03273","title":"Analysis of Convolutional Neural Networks for Document Image Classification","created":"2017-08-10","cited_by_count":13},{"id":"1704.01474","title":"Convolutional Neural Networks for Page Segmentation of Historical Document Images","created":"2017-04-05","cited_by_count":12},{"id":"2106.13500","title":"TableSense: Spreadsheet Table Detection with Convolutional Neural Networks","created":"2021-06-25","cited_by_count":12},{"id":"2010.02358","title":"VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach","created":"2020-10-05","cited_by_count":10},{"id":"1711.07695","title":"Fully Convolutional Neural Networks for Page Segmentation of Historical Document Images","created":"2017-11-21","cited_by_count":9}],"next_cursor":null}