{"list":"other","total":143,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"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":"1805.10123","title":"TADAM: Task dependent adaptive metric for improved few-shot learning","created":"2018-05-23","cited_by_count":408},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"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":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"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":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168},{"id":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","created":"2023-10-08","cited_by_count":143},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","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":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"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":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105},{"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":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100},{"id":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95},{"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":"1811.09362","title":"Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors","created":"2018-11-23","cited_by_count":89},{"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":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","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":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"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":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72},{"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":"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":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58},{"id":"2405.00334","title":"A Survey on Deep Active Learning: Recent Advances and New Frontiers","created":"2024-05-01","cited_by_count":54},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52},{"id":"2006.09073","title":"Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering","created":"2020-06-16","cited_by_count":51},{"id":"2109.11406","title":"Named Entity Recognition and Classification on Historical Documents: A Survey","created":"2021-09-23","cited_by_count":47},{"id":"1907.00490","title":"ICDAR 2019 Competition on Scene Text Visual Question Answering","created":"2019-06-30","cited_by_count":46},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46}],"next_cursor":"100"}