{"total":149,"rows":[{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"area":"mllm"},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245,"area":null},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229,"area":"diffusion"},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217,"area":"mllm"},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169,"area":null},{"id":"2305.14761","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","created":"2023-05-24","cited_by_count":160,"area":"mllm"},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140,"area":"diffusion"},{"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":"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":"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,"area":null},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","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":"2305.17718","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","created":"2023-05-28","cited_by_count":33,"area":"mllm"},{"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":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27,"area":null},{"id":"2402.11248","title":"CoLLaVO: Crayon Large Language and Vision mOdel","created":"2024-02-17","cited_by_count":26,"area":"mllm"},{"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":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23,"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":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"area":null},{"id":"2405.14701","title":"DreamText: High Fidelity Scene Text Synthesis","created":"2024-05-23","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":"2301.07464","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","created":"2023-01-18","cited_by_count":16,"area":"mllm"},{"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":"2406.01062","title":"Layout Agnostic Scene Text Image Synthesis with Diffusion Models","created":"2024-06-03","cited_by_count":14,"area":"diffusion"},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","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":"2401.07080","title":"GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching","created":"2024-01-13","cited_by_count":12,"area":null},{"id":"2409.04095","title":"UNIT: Unifying Image and Text Recognition in One Vision Encoder","created":"2024-09-06","cited_by_count":12,"area":null},{"id":"2405.13896","title":"A General Framework for Jersey Number Recognition in Sports Video","created":"2024-05-22","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":"2505.05853","title":"PICD: Versatile Perceptual Image Compression with Diffusion Rendering","created":"2025-05-09","cited_by_count":11,"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":"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":"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":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","cited_by_count":8,"area":null},{"id":"2402.03082","title":"Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing","created":"2024-02-05","cited_by_count":8,"area":null},{"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":"2406.11432","title":"AnyTrans: Translate AnyText in the Image with Large Scale Models","created":"2024-06-17","cited_by_count":8,"area":"diffusion"},{"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":"2412.01137","title":"TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition","created":"2024-12-02","cited_by_count":8,"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":"2509.05146","title":"PRIM: Towards Practical In-Image Multilingual Machine Translation","created":"2025-09-05","cited_by_count":7,"area":null},{"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":"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":"2308.03024","title":"Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation","created":"2023-08-06","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":"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":"2508.18425","title":"LPLC: A Dataset for License Plate Legibility Classification","created":"2025-08-25","cited_by_count":5,"area":null},{"id":"2604.05271","title":"Toward Unified Fine-Grained Vehicle Classification and Automatic License Plate Recognition","created":"2026-04-07","cited_by_count":5,"area":null},{"id":"2304.11966","title":"ICDAR 2023 Competition on Reading the Seal Title","created":"2023-04-24","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":"2311.17955","title":"PEAN: A Diffusion-Based Prior-Enhanced Attention Network for Scene Text Image Super-Resolution","created":"2023-11-29","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":"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":"2604.08741","title":"LPLCv2: An Expanded Dataset for Fine-Grained License Plate Legibility Classification","created":"2026-04-09","cited_by_count":4,"area":null},{"id":"2604.22506","title":"ICPR 2026 Competition on Low-Resolution License Plate Recognition","created":"2026-04-24","cited_by_count":4,"area":null},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2308.02770","title":"One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer","created":"2023-08-05","cited_by_count":3,"area":null},{"id":"2312.10806","title":"Cross-Lingual Learning in Multilingual Scene Text Recognition","created":"2023-12-17","cited_by_count":3,"area":null},{"id":"2403.02127","title":"LOCR: Location-Guided Transformer for Optical Character Recognition","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2410.19144","title":"Visual Text Matters: Improving Text-KVQA with Visual Text Entity Knowledge-aware Large Multimodal Assistant","created":"2024-10-24","cited_by_count":3,"area":"mllm"},{"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":"2306.14269","title":"Weakly Supervised Scene Text Generation for Low-resource Languages","created":"2023-06-25","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":"2401.05167","title":"Watermark Text Pattern Spotting in Document Images","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2402.15806","title":"Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition","created":"2024-02-24","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":"2411.15585","title":"Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2502.06172","title":"PLATTER: A Page-Level Handwritten Text Recognition System for Indic Scripts","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2511.23071","title":"Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2602.06450","title":"What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2606.24484","title":"Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods","created":"2026-06-23","cited_by_count":2,"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":"2306.03482","title":"Looking and Listening: Audio Guided Text Recognition","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2402.08643","title":"Learned Image Compression with Text Quality Enhancement","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2402.17134","title":"Efficiently Leveraging Linguistic Priors for Scene Text Spotting","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2403.08007","title":"IndicSTR12: A Dataset for Indic Scene Text Recognition","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2404.05967","title":"JSTR: Judgment Improves Scene Text Recognition","created":"2024-04-09","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":"2502.21242","title":"Towards long-term player tracking with graph hierarchies and domain-specific features","created":"2025-02-28","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":"2504.00410","title":"NCAP: Scene Text Image Super-Resolution with Non-CAtegorical Prior","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2508.21693","title":"Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2509.03615","title":"E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition","created":"2025-09-03","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":"2511.09448","title":"MCAD: Multimodal Context-Aware Audio Description Generation For Soccer","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2602.04030","title":"TiCLS : Tightly Coupled Language Text Spotter","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2604.00725","title":"A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR","created":"2026-04-01","cited_by_count":1,"area":"ssm"},{"id":"2605.08163","title":"MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2606.24333","title":"UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation","created":"2026-06-23","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}],"next_cursor":"100"}