{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"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":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"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":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"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":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"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":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"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":"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":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245},{"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":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174},{"id":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"2502.18443","title":"olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models","created":"2025-02-25","cited_by_count":125},{"id":"2108.04539","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","created":"2021-08-10","cited_by_count":104},{"id":"1609.03605","title":"Detecting Text in Natural Image with Connectionist Text Proposal Network","created":"2016-09-12","cited_by_count":85},{"id":"2403.19128","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","created":"2024-03-28","cited_by_count":74},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70},{"id":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62},{"id":"2405.14295","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","created":"2024-05-23","cited_by_count":62},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57},{"id":"2006.07491","title":"OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold","created":"2020-06-12","cited_by_count":53},{"id":"2406.08100","title":"Multimodal Table Understanding","created":"2024-06-12","cited_by_count":44},{"id":"1804.10371","title":"dhSegment: A generic deep-learning approach for document segmentation","created":"2018-04-27","cited_by_count":32},{"id":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27},{"id":"2102.11838","title":"Page Layout Analysis System for Unconstrained Historic Documents","created":"2021-02-23","cited_by_count":20},{"id":"1604.00187","title":"PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents","created":"2016-04-01","cited_by_count":18},{"id":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12},{"id":"2104.13037","title":"AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions","created":"2021-04-27","cited_by_count":10},{"id":"2407.09103","title":"DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents","created":"2024-07-12","cited_by_count":9},{"id":"2502.04223","title":"\\'Eclair -- Extracting Content and Layout with Integrated Reading Order for Documents","created":"2025-02-06","cited_by_count":9},{"id":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","cited_by_count":8},{"id":"1703.07645","title":"Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript Collections","created":"2017-03-22","cited_by_count":7},{"id":"2103.05489","title":"TS-Net: OCR Trained to Switch Between Text Transcription Styles","created":"2021-03-09","cited_by_count":7},{"id":"1505.07778","title":"Query by String word spotting based on character bi-gram indexing","created":"2015-05-28","cited_by_count":4},{"id":"2303.03127","title":"ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents","created":"2023-03-06","cited_by_count":3},{"id":"2308.03515","title":"Keyword Spotting Simplified: A Segmentation-Free Approach using Character Counting and CTC re-scoring","created":"2023-08-07","cited_by_count":1}],"next_cursor":null}