{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"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":"1911.00068","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","created":"2019-10-31","cited_by_count":413},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"2001.10528","title":"Identifying Mislabeled Data using the Area Under the Margin Ranking","created":"2020-01-28","cited_by_count":261},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","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":"1803.11285","title":"Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking","created":"2018-03-29","cited_by_count":191},{"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":"2008.02637","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","created":"2020-08-06","cited_by_count":138},{"id":"1806.09029","title":"Improving Text-to-SQL Evaluation Methodology","created":"2018-06-23","cited_by_count":135},{"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":"1812.06469","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","created":"2018-12-16","cited_by_count":126},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"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":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"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":"1606.02858","title":"A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task","created":"2016-06-09","cited_by_count":72},{"id":"2005.00636","title":"We Need to Talk About Random Splits","created":"2020-05-01","cited_by_count":71},{"id":"2102.01818","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","created":"2021-02-03","cited_by_count":70},{"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":"1902.00423","title":"Do We Train on Test Data? Purging CIFAR of Near-Duplicates","created":"2019-02-01","cited_by_count":62},{"id":"2301.05456","title":"Data Quality for Software Vulnerability Datasets","created":"2023-01-13","cited_by_count":51},{"id":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39},{"id":"2202.12985","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","created":"2022-02-25","cited_by_count":35},{"id":"1904.03122","title":"Outlier Detection for Improved Data Quality and Diversity in Dialog Systems","created":"2019-04-05","cited_by_count":28},{"id":"1912.05283","title":"Identifying Mislabeled Instances in Classification Datasets","created":"2019-12-11","cited_by_count":26},{"id":"1701.02877","title":"Generalisation in Named Entity Recognition: A Quantitative Analysis","created":"2017-01-11","cited_by_count":25},{"id":"1907.06370","title":"Multimodal deep networks for text and image-based document classification","created":"2019-07-15","cited_by_count":24},{"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":"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":"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":"2212.09621","title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","created":"2022-12-19","cited_by_count":20},{"id":"2206.13155","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","created":"2022-06-27","cited_by_count":18},{"id":"2205.12702","title":"Detecting Label Errors by using Pre-Trained Language Models","created":"2022-05-25","cited_by_count":16},{"id":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16},{"id":"1912.04376","title":"Modular Multimodal Architecture for Document Classification","created":"2019-12-09","cited_by_count":15},{"id":"2205.12029","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification","created":"2022-05-24","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":"2006.09141","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","created":"2020-06-16","cited_by_count":11},{"id":"2211.14958","title":"MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding","created":"2022-11-27","cited_by_count":9},{"id":"2201.06219","title":"An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets","created":"2022-01-17","cited_by_count":8},{"id":"2101.00160","title":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","created":"2021-01-01","cited_by_count":7},{"id":"2109.01078","title":"Skim-Attention: Learning to Focus via Document Layout","created":"2021-09-02","cited_by_count":7},{"id":"2208.08201","title":"Understanding Long Documents with Different Position-Aware Attentions","created":"2022-08-17","cited_by_count":7},{"id":"1603.01076","title":"What is the right way to represent document images?","created":"2016-03-03","cited_by_count":5},{"id":"2205.08094","title":"MATrIX -- Modality-Aware Transformer for Information eXtraction","created":"2022-05-17","cited_by_count":2},{"id":"2301.07502","title":"Multimodal Side-Tuning for Document Classification","created":"2023-01-16","cited_by_count":2}],"next_cursor":null}