{"total":114,"rows":[{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194,"area":null},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149,"area":null},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97,"area":null},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94,"area":null},{"id":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74,"area":null},{"id":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58,"area":"diffusion"},{"id":"2106.08385","title":"TextStyleBrush: Transfer of Text Aesthetics from a Single Example","created":"2021-06-15","cited_by_count":49,"area":null},{"id":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"id":"2104.07787","title":"Rethinking Text Line Recognition Models","created":"2021-04-15","cited_by_count":45,"area":null},{"id":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44,"area":null},{"id":"2107.09313","title":"SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models","created":"2021-07-20","cited_by_count":43,"area":null},{"id":"2211.10578","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","created":"2022-11-19","cited_by_count":40,"area":null},{"id":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40,"area":null},{"id":"2308.04047","title":"SODFormer: Streaming Object Detection with Transformer Using Events and Frames","created":"2023-08-08","cited_by_count":39,"area":null},{"id":"2111.11011","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","created":"2021-11-22","cited_by_count":36,"area":null},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36,"area":null},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33,"area":null},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2503.23461","title":"Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generation","created":"2025-03-30","cited_by_count":25,"area":null},{"id":"2107.12090","title":"Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition","created":"2021-07-26","cited_by_count":24,"area":null},{"id":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24,"area":null},{"id":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23,"area":null},{"id":"2311.11268","title":"Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters","created":"2023-11-19","cited_by_count":22,"area":null},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22,"area":null},{"id":"2303.04291","title":"Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition","created":"2023-03-07","cited_by_count":20,"area":"diffusion"},{"id":"2303.13095","title":"Modeling Entities as Semantic Points for Visual Information Extraction in the Wild","created":"2023-03-23","cited_by_count":20,"area":null},{"id":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"id":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"area":null},{"id":"2504.21682","title":"Visual Text Processing: A Comprehensive Review and Unified Evaluation","created":"2025-04-30","cited_by_count":19,"area":null},{"id":"2103.15992","title":"A Multiplexed Network for End-to-End, Multilingual OCR","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18,"area":"mllm"},{"id":"2305.05140","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","created":"2023-05-09","cited_by_count":18,"area":null},{"id":"2107.12087","title":"Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation","created":"2021-07-26","cited_by_count":17,"area":"distill"},{"id":"2203.04814","title":"Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2205.03873","title":"Multimodal Semi-Supervised Learning for Text Recognition","created":"2022-05-08","cited_by_count":16,"area":null},{"id":"2302.10414","title":"Improving Scene Text Image Super-resolution via Dual Prior Modulation Network","created":"2023-02-21","cited_by_count":15,"area":null},{"id":"2209.00641","title":"Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition","created":"2022-08-31","cited_by_count":14,"area":null},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2305.01443","title":"Scalable Mask Annotation for Video Text Spotting","created":"2023-05-02","cited_by_count":13,"area":null},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2308.07202","title":"Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning","created":"2023-08-14","cited_by_count":12,"area":null},{"id":"2408.00355","title":"DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training","created":"2024-08-01","cited_by_count":11,"area":null},{"id":"2505.22810","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2604.12890","title":"Towards Long-horizon Agentic Multimodal Search","created":"2026-04-14","cited_by_count":11,"area":"agents"},{"id":"2308.06743","title":"TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution","created":"2023-08-13","cited_by_count":10,"area":"diffusion"},{"id":"2402.13643","title":"Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition","created":"2024-02-21","cited_by_count":10,"area":null},{"id":"2211.04963","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2305.05322","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2308.08806","title":"Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach","created":"2023-08-17","cited_by_count":8,"area":"distill"},{"id":"2310.12430","title":"DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond","created":"2023-10-19","cited_by_count":8,"area":null},{"id":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","cited_by_count":8,"area":null},{"id":"2401.14832","title":"Text Image Inpainting via Global Structure-Guided Diffusion Models","created":"2024-01-26","cited_by_count":8,"area":"diffusion"},{"id":"2305.19957","title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2307.13244","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2202.11221","title":"Arbitrary Shape Text Detection using Transformers","created":"2022-02-22","cited_by_count":6,"area":null},{"id":"2207.12955","title":"Contextual Text Block Detection towards Scene Text Understanding","created":"2022-07-26","cited_by_count":6,"area":null},{"id":"2102.07343","title":"Capturing Detailed Deformations of Moving Human Bodies","created":"2021-02-15","cited_by_count":5,"area":null},{"id":"2103.04635","title":"FEDS -- Filtered Edit Distance Surrogate","created":"2021-03-08","cited_by_count":5,"area":null},{"id":"2112.00948","title":"Visual-Semantic Transformer for Scene Text Recognition","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2209.13139","title":"Searching a High-Performance Feature Extractor for Text Recognition Network","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2211.12950","title":"Look, Read and Ask: Learning to Ask Questions by Reading Text in Images","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2505.22228","title":"GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2305.16172","title":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2306.06823","title":"Weakly supervised information extraction from inscrutable handwritten document images","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2404.12734","title":"Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2505.17473","title":"InfoDet: A Dataset for Infographic Element Detection","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2209.14970","title":"3D Rendering Framework for Data Augmentation in Optical Character Recognition","created":"2022-09-27","cited_by_count":3,"area":null},{"id":"2210.07423","title":"Task Grouping for Multilingual Text Recognition","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2308.15004","title":"PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2308.15037","title":"Is it an i or an l: Test-time Adaptation of Text Line Recognition Models","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2407.19889","title":"Self-Supervised Learning for Text Recognition: A Critical Survey","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2507.02200","title":"ESTR-CoT: Towards Explainable and Accurate Event Stream based Scene Text Recognition with Chain-of-Thought Reasoning","created":"2025-07-02","cited_by_count":3,"area":"lr"},{"id":"2508.14557","title":"Improving OCR using internal document redundancy","created":"2025-08-20","cited_by_count":3,"area":null},{"id":"2105.15093","title":"Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition","created":"2021-05-31","cited_by_count":2,"area":null},{"id":"2108.06881","title":"Text-Aware Single Image Specular Highlight Removal","created":"2021-08-16","cited_by_count":2,"area":null},{"id":"2111.08314","title":"TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance","created":"2021-11-16","cited_by_count":2,"area":null},{"id":"2201.04014","title":"Captcha Attack: Turning Captchas Against Humanity","created":"2022-01-11","cited_by_count":2,"area":null},{"id":"2212.00377","title":"Domain Adaptive Scene Text Detection via Subcategorization","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2303.16531","title":"RusTitW: Russian Language Text Dataset for Visual Text in-the-Wild Recognition","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2309.00410","title":"Selective Scene Text Removal","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2408.14805","title":"Platypus: A Generalized Specialist Model for Reading Text in Various Forms","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2108.06166","title":"IFR: Iterative Fusion Based Recognizer For Low Quality Scene Text Recognition","created":"2021-08-13","cited_by_count":1,"area":null},{"id":"2111.12276","title":"Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2111.13327","title":"Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition","created":"2021-11-26","cited_by_count":1,"area":null},{"id":"2112.10587","title":"Image-free multi-character recognition","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2302.05105","title":"Text recognition on images using pre-trained CNN","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2401.09232","title":"Dynamic Relation Transformer for Contextual Text Block Detection","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2401.11704","title":"EK-Net:Real-time Scene Text Detection with Expand Kernel Distance","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2409.00447","title":"The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts","created":"2024-08-31","cited_by_count":1,"area":null},{"id":"2102.04568","title":"Tracking e-cigarette warning label compliance on Instagram with deep learning","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2107.05279","title":"ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment","created":"2021-07-12","cited_by_count":0,"area":null},{"id":"2210.10836","title":"Scene Text Recognition with Semantics","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2211.05036","title":"Portmanteauing Features for Scene Text Recognition","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2303.15737","title":"Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2307.15029","title":"Adaptive Segmentation Network for Scene Text Detection","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2311.13222","title":"Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approach","created":"2023-11-22","cited_by_count":0,"area":null},{"id":"2311.16555","title":"Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models","created":"2023-11-28","cited_by_count":0,"area":"diffusion"},{"id":"2312.11153","title":"Research on Multilingual Natural Scene Text Detection Algorithm","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2502.09026","title":"Billet Number Recognition Based on Test-Time Adaptation","created":"2025-02-13","cited_by_count":0,"area":null}],"next_cursor":"100"}