{"total":81,"rows":[{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279,"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":"2205.00159","title":"SVTR: Scene Text Recognition with a Single Visual Model","created":"2022-04-30","cited_by_count":88,"area":null},{"id":"2403.09622","title":"Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering","created":"2024-03-14","cited_by_count":81,"area":null},{"id":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62,"area":null},{"id":"2312.04884","title":"UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models","created":"2023-12-08","cited_by_count":59,"area":"diffusion"},{"id":"2305.16318","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","created":"2023-05-25","cited_by_count":54,"area":null},{"id":"2410.10133","title":"TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control","created":"2024-10-14","cited_by_count":45,"area":null},{"id":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40,"area":null},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36,"area":null},{"id":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34,"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":"2203.03382","title":"Self-supervised Implicit Glyph Attention for Text Recognition","created":"2022-03-07","cited_by_count":25,"area":null},{"id":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24,"area":null},{"id":"2201.00267","title":"On the Cross-dataset Generalization in License Plate Recognition","created":"2022-01-02","cited_by_count":22,"area":null},{"id":"2405.14701","title":"DreamText: High Fidelity Scene Text Synthesis","created":"2024-05-23","cited_by_count":18,"area":null},{"id":"2205.03873","title":"Multimodal Semi-Supervised Learning for Text Recognition","created":"2022-05-08","cited_by_count":16,"area":null},{"id":"2301.07464","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","created":"2023-01-18","cited_by_count":16,"area":"mllm"},{"id":"2304.04653","title":"Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition","created":"2023-04-10","cited_by_count":14,"area":null},{"id":"2310.04999","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","created":"2023-10-08","cited_by_count":14,"area":"distill"},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2401.10222","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2312.11923","title":"IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2309.04331","title":"Leveraging Model Fusion for Improved License Plate Recognition","created":"2023-09-08","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":"2307.15045","title":"A Transformer-based Approach for Arabic Offline Handwritten Text Recognition","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2412.00151","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","created":"2024-11-29","cited_by_count":8,"area":"lr"},{"id":"2412.13871","title":"LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer","created":"2024-12-18","cited_by_count":8,"area":"mllm"},{"id":"2306.16707","title":"DiffusionSTR: Diffusion Model for Scene Text Recognition","created":"2023-06-29","cited_by_count":7,"area":"diffusion"},{"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":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2405.11180","title":"GestFormer: Multiscale Wavelet Pooling Transformer Network for Dynamic Hand Gesture Recognition","created":"2024-05-18","cited_by_count":7,"area":null},{"id":"2601.07671","title":"Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluation","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2503.18746","title":"Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2108.06949","title":"Data Augmentation for Scene Text Recognition","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2212.05525","title":"Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images","created":"2022-12-11","cited_by_count":5,"area":null},{"id":"2401.10110","title":"SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor","created":"2024-01-18","cited_by_count":5,"area":null},{"id":"2303.10848","title":"Weakly-Supervised Text Instance Segmentation","created":"2023-03-20","cited_by_count":4,"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":"2409.11656","title":"VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2304.08592","title":"Improving Scene Text Recognition for Character-Level Long-Tailed Distribution","created":"2023-03-31","cited_by_count":3,"area":null},{"id":"2107.13938","title":"Why You Should Try the Real Data for the Scene Text Recognition","created":"2021-07-29","cited_by_count":2,"area":null},{"id":"2201.02850","title":"Image-based Automatic Dial Meter Reading in Unconstrained Scenarios","created":"2022-01-08","cited_by_count":2,"area":null},{"id":"2205.08565","title":"Text Detection & Recognition in the Wild for Robot Localization","created":"2022-05-17","cited_by_count":2,"area":null},{"id":"2210.16901","title":"Foreign Object Debris Detection for Airport Pavement Images based on Self-supervised Localization and Vision Transformer","created":"2022-10-30","cited_by_count":2,"area":null},{"id":"2212.09297","title":"Transferring General Multimodal Pretrained Models to Text Recognition","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2306.15782","title":"UTRNet: High-Resolution Urdu Text Recognition In Printed Documents","created":"2023-06-27","cited_by_count":2,"area":null},{"id":"2310.00558","title":"Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes","created":"2023-10-01","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":"2408.14998","title":"FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2211.04785","title":"Masked Vision-Language Transformers for Scene Text Recognition","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2211.13194","title":"Indian Commercial Truck License Plate Detection and Recognition for Weighbridge Automation","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2312.01177","title":"IDPL-PFOD2: A New Large-Scale Dataset for Printed Farsi Optical Character Recognition","created":"2023-12-02","cited_by_count":1,"area":null},{"id":"2407.05562","title":"Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2503.13060","title":"Historic Scripts to Modern Vision: A Novel Dataset and A VLM Framework for Transliteration of Modi Script to Devanagari","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2506.06761","title":"The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2510.01651","title":"LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2607.13458","title":"2D Rotary Position Embedding for Scene Text Recognition with Transformers","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2302.14261","title":"Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2307.16410","title":"HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2310.09549","title":"Scene Text Recognition Models Explainability Using Local Features","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2311.09256","title":"Reading Between the Mud: A Challenging Motorcycle Racer Number Dataset","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2312.00174","title":"Compression of end-to-end non-autoregressive image-to-speech system for low-resourced devices","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2401.05338","title":"STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2401.09823","title":"Enhancing Small Object Encoding in Deep Neural Networks: Introducing Fast&Focused-Net with Volume-wise Dot Product Layer","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2402.08025","title":"Beyond the Mud: Datasets and Benchmarks for Computer Vision in Off-Road Racing","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2403.07518","title":"Open-Vocabulary Scene Text Recognition via Pseudo-Image Labeling and Margin Loss","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2405.09125","title":"HAAP: Vision-context Hierarchical Attention Autoregressive with Adaptive Permutation for Scene Text Recognition","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2407.16204","title":"CLII: Visual-Text Inpainting via Cross-Modal Predictive Interaction","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2409.14483","title":"One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance","created":"2024-09-22","cited_by_count":0,"area":null},{"id":"2410.09913","title":"Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2503.15639","title":"A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2503.16184","title":"Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation","created":"2025-03-20","cited_by_count":0,"area":"distill"},{"id":"2504.11164","title":"Learning Attribute-aware Representations for Few-shot Scene Text Segmentation","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2508.01153","title":"TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2508.01802","title":"SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spotting","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2511.08133","title":"OTSNet: A Neurocognitive-Inspired Observation-Thinking-Spelling Pipeline for Scene Text Recognition","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.14050","title":"SELECT: Detecting Label Errors in Real-world Scene Text Data","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2607.23194","title":"Out-of-Length Scene Text Recognition: A Two-Axis Diagnosis and a Training-Free Fix","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.29970","title":"Confidence-Aware Ensemble and Long-Word Refinement for Artistic Text Recognition","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.39684","title":"Unapologetically Distributed: A Call for Decentralized Document Analysis","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}