{"total":194,"rows":[{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"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":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229,"area":"diffusion"},{"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,"area":"mllm"},{"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":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"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,"area":null},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66,"area":null},{"id":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58,"area":"diffusion"},{"id":"2112.15093","title":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","created":"2021-12-30","cited_by_count":53,"area":null},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53,"area":null},{"id":"2310.16809","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","created":"2023-10-25","cited_by_count":46,"area":null},{"id":"2207.00193","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","created":"2022-07-01","cited_by_count":45,"area":null},{"id":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45,"area":null},{"id":"2304.05568","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","created":"2023-04-12","cited_by_count":45,"area":"diffusion"},{"id":"2305.10825","title":"DiffUTE: Universal Text Editing Diffusion Model","created":"2023-05-18","cited_by_count":45,"area":"diffusion"},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45,"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":"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":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40,"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":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2202.12985","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","created":"2022-02-25","cited_by_count":35,"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":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","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":"2308.10147","title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","created":"2023-08-20","cited_by_count":29,"area":null},{"id":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27,"area":null},{"id":"2204.14044","title":"C3-STISR: Scene Text Image Super-resolution with Triple Clues","created":"2022-04-29","cited_by_count":26,"area":null},{"id":"2309.01083","title":"Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning","created":"2023-09-03","cited_by_count":26,"area":null},{"id":"2112.12916","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","created":"2021-12-24","cited_by_count":25,"area":null},{"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":"2411.15858","title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","created":"2024-11-24","cited_by_count":24,"area":null},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22,"area":null},{"id":"2203.10492","title":"SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization","created":"2022-03-20","cited_by_count":21,"area":null},{"id":"2306.03287","title":"ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"area":null},{"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":"2401.17851","title":"Instruction-Guided Scene Text Recognition","created":"2024-01-31","cited_by_count":17,"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":"2410.10168","title":"First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending","created":"2024-10-14","cited_by_count":16,"area":"diffusion"},{"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":"2311.09759","title":"Scene Text Image Super-resolution based on Text-conditional Diffusion Models","created":"2023-11-16","cited_by_count":15,"area":"diffusion"},{"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":"2512.21095","title":"UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters","created":"2025-12-24","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":"2502.08417","title":"Handwritten Text Recognition: A Survey","created":"2025-02-12","cited_by_count":12,"area":null},{"id":"2503.08387","title":"Recognition-Synergistic Scene Text Editing","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2105.03906","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","created":"2021-05-09","cited_by_count":11,"area":null},{"id":"2209.06717","title":"Out-of-Vocabulary Challenge Report","created":"2022-09-14","cited_by_count":11,"area":null},{"id":"2407.12317","title":"Out of Length Text Recognition with Sub-String Matching","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2207.10256","title":"SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition","created":"2022-07-21","cited_by_count":10,"area":null},{"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":"2304.04376","title":"ICDAR 2023 Video Text Reading Competition for Dense and Small Text","created":"2023-04-10","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":"2404.04624","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","created":"2024-04-06","cited_by_count":9,"area":null},{"id":"2404.05595","title":"UniFL: Improve Latent Diffusion Model via Unified Feedback Learning","created":"2024-04-08","cited_by_count":9,"area":"diffusion"},{"id":"2407.11502","title":"How Control Information Influences Multilingual Text Image Generation and Editing?","created":"2024-07-16","cited_by_count":9,"area":"diffusion"},{"id":"2603.24373","title":"PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks","created":"2026-03-25","cited_by_count":9,"area":"mllm"},{"id":"2204.05535","title":"Open-set Text Recognition via Character-Context Decoupling","created":"2022-04-12","cited_by_count":8,"area":null},{"id":"2307.09749","title":"Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement","created":"2023-07-19","cited_by_count":8,"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":"2401.14832","title":"Text Image Inpainting via Global Structure-Guided Diffusion Models","created":"2024-01-26","cited_by_count":8,"area":"diffusion"},{"id":"2405.05841","title":"Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2412.01137","title":"TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2204.07714","title":"Pushing the Performance Limit of Scene Text Recognizer without Human Annotation","created":"2022-04-16","cited_by_count":7,"area":null},{"id":"2305.14758","title":"MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition","created":"2023-05-24","cited_by_count":7,"area":null},{"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":"2503.13385","title":"Scale Efficient Training for Large Datasets","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2308.00508","title":"Relational Contrastive Learning for Scene Text Recognition","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2311.00734","title":"On Manipulating Scene Text in the Wild with Diffusion Models","created":"2023-11-01","cited_by_count":6,"area":"diffusion"},{"id":"2311.13317","title":"Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution","created":"2023-11-22","cited_by_count":6,"area":"diffusion"},{"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":"2506.09993","title":"Text-Aware Image Restoration with Diffusion Models","created":"2025-06-11","cited_by_count":6,"area":"diffusion"},{"id":"2507.02790","title":"From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding","created":"2025-07-03","cited_by_count":6,"area":null},{"id":"2105.08383","title":"I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition","created":"2021-05-18","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":"2401.07641","title":"SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2403.10047","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2212.14674","title":"A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition","created":"2022-12-27","cited_by_count":4,"area":null},{"id":"2303.10848","title":"Weakly-Supervised Text Instance Segmentation","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2305.11373","title":"Deep Image Compression Using Scene Text Quality Assessment","created":"2023-05-19","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":"2308.10493","title":"Semantic Graph Representation Learning for Handwritten Mathematical Expression Recognition","created":"2023-08-21","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":"2409.17095","title":"General Detection-based Text Line Recognition","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2410.22829","title":"Situational Scene Graph for Structured Human-centric Situation Understanding","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2511.05818","title":"LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2512.01422","title":"MDiff4STR: Mask Diffusion Model for Scene Text Recognition","created":"2025-12-01","cited_by_count":4,"area":"diffusion"},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null}],"next_cursor":"100"}