{"list":"other","total":77,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"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":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"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":"1603.01354","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","created":"2016-03-04","cited_by_count":341},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"1703.01086","title":"Arbitrary-Oriented Scene Text Detection via Rotation Proposals","created":"2017-03-03","cited_by_count":176},{"id":"1908.08207","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","created":"2019-08-22","cited_by_count":171},{"id":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2009.09941","title":"PP-OCR: A Practical Ultra Lightweight OCR System","created":"2020-09-21","cited_by_count":151},{"id":"1903.12473","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","created":"2019-03-28","cited_by_count":147},{"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":"1412.1842","title":"Reading Text in the Wild with Convolutional Neural Networks","created":"2014-12-04","cited_by_count":122},{"id":"1611.06779","title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","created":"2016-11-21","cited_by_count":119},{"id":"1801.02765","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","created":"2018-01-09","cited_by_count":119},{"id":"1910.11470","title":"A Survey on Recent Advances in Named Entity Recognition from Deep Learning models","created":"2019-10-25","cited_by_count":117},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"id":"1807.01544","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","created":"2018-07-04","cited_by_count":114},{"id":"1709.02054","title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","created":"2017-09-07","cited_by_count":110},{"id":"1801.01671","title":"FOTS: Fast Oriented Text Spotting with a Unified Network","created":"2018-01-05","cited_by_count":109},{"id":"1809.08799","title":"Chargrid: Towards Understanding 2D Documents","created":"2018-09-24","cited_by_count":100},{"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":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90},{"id":"1803.05265","title":"Rotation-Sensitive Regression for Oriented Scene Text Detection","created":"2018-03-14","cited_by_count":88},{"id":"1903.11279","title":"Graph Convolution for Multimodal Information Extraction from Visually Rich Documents","created":"2019-03-27","cited_by_count":88},{"id":"1703.06520","title":"Detecting Oriented Text in Natural Images by Linking Segments","created":"2017-03-19","cited_by_count":80},{"id":"1603.03101","title":"Recursive Recurrent Nets with Attention Modeling for OCR in the Wild","created":"2016-03-09","cited_by_count":74},{"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":"1910.05085","title":"Rosetta: Large scale system for text detection and recognition in images","created":"2019-10-11","cited_by_count":69},{"id":"1904.06535","title":"Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes","created":"2019-04-13","cited_by_count":66},{"id":"1911.09550","title":"All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting","created":"2019-11-21","cited_by_count":66},{"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":"1707.03985","title":"Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks","created":"2017-07-13","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":"2002.06820","title":"Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting","created":"2020-02-17","cited_by_count":51},{"id":"2012.04350","title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","created":"2020-12-08","cited_by_count":51},{"id":"1803.03474","title":"An end-to-end TextSpotter with Explicit Alignment and Attention","created":"2018-03-09","cited_by_count":50},{"id":"1812.01393","title":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection","created":"2018-12-04","cited_by_count":50},{"id":"1810.13083","title":"GraphIE: A Graph-Based Framework for Information Extraction","created":"2018-10-31","cited_by_count":45},{"id":"2103.14470","title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","created":"2021-03-26","cited_by_count":43},{"id":"1811.08605","title":"Scene Text Detection with Supervised Pyramid Context Network","created":"2018-11-21","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":"1703.01425","title":"Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection","created":"2017-03-04","cited_by_count":31},{"id":"1709.00138","title":"Single Shot Text Detector with Regional Attention","created":"2017-09-01","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":"2005.03492","title":"Text Recognition in the Wild: A Survey","created":"2020-05-07","cited_by_count":29},{"id":"2003.02356","title":"Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout","created":"2020-03-04","cited_by_count":27},{"id":"1812.07248","title":"Attend, Copy, Parse -- End-to-end information extraction from documents","created":"2018-12-18","cited_by_count":25},{"id":"1811.07460","title":"Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection","created":"2018-11-19","cited_by_count":22},{"id":"1903.12363","title":"CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor","created":"2019-03-29","cited_by_count":21},{"id":"2001.04351","title":"CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese","created":"2020-01-13","cited_by_count":19},{"id":"2106.12940","title":"MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction","created":"2021-06-24","cited_by_count":18},{"id":"1903.08836","title":"Towards Robust Curve Text Detection with Conditional Spatial Expansion","created":"2019-03-21","cited_by_count":16},{"id":"1912.10016","title":"A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages","created":"2019-12-20","cited_by_count":16},{"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":"1907.12791","title":"Towards Pure End-to-End Learning for Recognizing Multiple Text Sequences from an Image","created":"2019-07-30","cited_by_count":1}],"next_cursor":null}