{"list":"other","total":96,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"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":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485},{"id":"2012.06678","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","created":"2020-12-11","cited_by_count":409},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"2409.18839","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","created":"2024-09-27","cited_by_count":267},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245},{"id":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"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":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180},{"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":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148},{"id":"2005.00589","title":"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context","created":"2020-05-01","cited_by_count":147},{"id":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"2110.00061","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","created":"2021-09-30","cited_by_count":126},{"id":"1603.03915","title":"Robust Scene Text Recognition with Automatic Rectification","created":"2016-03-12","cited_by_count":121},{"id":"1611.06779","title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","created":"2016-11-21","cited_by_count":119},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"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":"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":"2108.09661","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","created":"2021-08-22","cited_by_count":97},{"id":"2203.01017","title":"TableFormer: Table Structure Understanding with Transformers","created":"2022-03-02","cited_by_count":94},{"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":"1908.04729","title":"Complicated Table Structure Recognition","created":"2019-08-13","cited_by_count":92},{"id":"2410.12628","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","created":"2024-10-16","cited_by_count":82},{"id":"1609.04938","title":"Image-to-Markup Generation with Coarse-to-Fine Attention","created":"2016-09-16","cited_by_count":79},{"id":"2408.07246","title":"ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area","created":"2024-08-14","cited_by_count":71},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70},{"id":"2003.11288","title":"SCATTER: Selective Context Attentional Scene Text Recognizer","created":"2020-03-25","cited_by_count":69},{"id":"2203.01601","title":"Syntax-Aware Network for Handwritten Mathematical Expression Recognition","created":"2022-03-03","cited_by_count":68},{"id":"1909.04948","title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","created":"2019-09-11","cited_by_count":63},{"id":"1801.01315","title":"PixelLink: Detecting Scene Text via Instance Segmentation","created":"2018-01-04","cited_by_count":60},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53},{"id":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46},{"id":"2409.03277","title":"ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding","created":"2024-09-05","cited_by_count":46},{"id":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45},{"id":"2109.02199","title":"Parsing Table Structures in the Wild","created":"2021-09-06","cited_by_count":43},{"id":"2107.05214","title":"Split, embed and merge: An accurate table structure recognizer","created":"2021-07-12","cited_by_count":42},{"id":"2404.15254","title":"UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition","created":"2024-04-23","cited_by_count":42},{"id":"2303.06949","title":"Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling","created":"2023-03-13","cited_by_count":41},{"id":"2105.01848","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","created":"2021-05-05","cited_by_count":39},{"id":"1804.02445","title":"Extracting Scientific Figures with Distantly Supervised Neural Networks","created":"2018-04-06","cited_by_count":36},{"id":"2406.11633","title":"DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models","created":"2024-06-17","cited_by_count":36},{"id":"2207.11463","title":"When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition","created":"2022-07-23","cited_by_count":35},{"id":"2011.13534","title":"A Survey of Deep Learning Approaches for OCR and Document Understanding","created":"2020-11-27","cited_by_count":32},{"id":"2106.10598","title":"TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition","created":"2021-06-20","cited_by_count":27},{"id":"2208.04921","title":"TSRFormer: Table Structure Recognition with Transformers","created":"2022-08-09","cited_by_count":27},{"id":"2003.13197","title":"Cross-Domain Document Object Detection: Benchmark Suite and Method","created":"2020-03-30","cited_by_count":24},{"id":"2207.04410","title":"CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition","created":"2022-07-10","cited_by_count":24},{"id":"2303.14884","title":"A large-scale dataset for end-to-end table recognition in the wild","created":"2023-03-27","cited_by_count":24},{"id":"1710.05703","title":"A Survey on Optical Character Recognition System","created":"2017-10-03","cited_by_count":23},{"id":"2404.10690","title":"MathWriting: A Dataset For Handwritten Mathematical Expression Recognition","created":"2024-04-16","cited_by_count":21},{"id":"2001.02501","title":"Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks","created":"2020-01-08","cited_by_count":20},{"id":"2208.14687","title":"TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers","created":"2022-08-31","cited_by_count":19},{"id":"2003.07560","title":"GFTE: Graph-based Financial Table Extraction","created":"2020-03-17","cited_by_count":17},{"id":"2111.07129","title":"Visual Understanding of Complex Table Structures from Document Images","created":"2021-11-13","cited_by_count":17},{"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":"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":"2211.08469","title":"Deep learning for table detection and structure recognition: A survey","created":"2022-11-15","cited_by_count":15},{"id":"2403.04822","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","created":"2024-03-07","cited_by_count":13},{"id":"2303.04384","title":"SEMv2: Table Separation Line Detection Based on Instance Segmentation","created":"2023-03-08","cited_by_count":12},{"id":"2303.11615","title":"Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer","created":"2023-03-21","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":"2105.02039","title":"Towards an efficient framework for Data Extraction from Chart Images","created":"2021-05-05","cited_by_count":10},{"id":"2303.07641","title":"Rethinking Image-based Table Recognition Using Weakly Supervised Methods","created":"2023-03-14","cited_by_count":10},{"id":"2408.08578","title":"TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition","created":"2024-08-16","cited_by_count":9},{"id":"1806.08852","title":"Multi-Task Handwritten Document Layout Analysis","created":"2018-06-22","cited_by_count":8},{"id":"2308.02051","title":"A Graphical Approach to Document Layout Analysis","created":"2023-08-03","cited_by_count":8},{"id":"2210.17246","title":"Tables to LaTeX: structure and content extraction from scientific tables","created":"2022-10-31","cited_by_count":7},{"id":"2305.19181","title":"Table Detection for Visually Rich Document Images","created":"2023-05-30","cited_by_count":6},{"id":"2404.01743","title":"Atom-Level Optical Chemical Structure Recognition with Limited Supervision","created":"2024-04-02","cited_by_count":5},{"id":"2209.09207","title":"Table Detection in the Wild: A Novel Diverse Table Detection Dataset and Method","created":"2022-08-31","cited_by_count":4},{"id":"2408.16123","title":"ChartEye: A Deep Learning Framework for Chart Information Extraction","created":"2024-08-28","cited_by_count":4},{"id":"2003.08005","title":"ScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images","created":"2020-03-18","cited_by_count":3},{"id":"2403.02127","title":"LOCR: Location-Guided Transformer for Optical Character Recognition","created":"2024-03-04","cited_by_count":3},{"id":"2304.13240","title":"Structure Diagram Recognition in Financial Announcements","created":"2023-04-26","cited_by_count":1},{"id":"2409.04683","title":"C2F-CHART: A Curriculum Learning Approach to Chart Classification","created":"2024-09-07","cited_by_count":1}],"next_cursor":null}