{"total":139,"rows":[{"id":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174,"area":"mllm"},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171,"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":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106,"area":null},{"id":"2403.20271","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","created":"2024-03-29","cited_by_count":101,"area":"mllm"},{"id":"2108.09661","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","created":"2021-08-22","cited_by_count":97,"area":"mllm"},{"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":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93,"area":null},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84,"area":null},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","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":"2103.04400","title":"What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels","created":"2021-03-07","cited_by_count":63,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50,"area":null},{"id":"2106.12326","title":"Open Images V5 Text Annotation and Yet Another Mask Text Spotter","created":"2021-06-23","cited_by_count":46,"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":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","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":"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":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44,"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":"2109.03144","title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","created":"2021-09-07","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":"2207.11934","title":"Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning","created":"2022-07-25","cited_by_count":33,"area":null},{"id":"2410.05261","title":"TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens","created":"2024-10-07","cited_by_count":32,"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":"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":"2305.17415","title":"Exploring Better Text Image Translation with Multimodal Codebook","created":"2023-05-27","cited_by_count":23,"area":null},{"id":"2104.11493","title":"Stroke-Based Scene Text Erasing Using Synthetic Data for Training","created":"2021-04-23","cited_by_count":20,"area":null},{"id":"2506.05344","title":"SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs","created":"2025-06-05","cited_by_count":20,"area":"mllm"},{"id":"2103.15992","title":"A Multiplexed Network for End-to-End, Multilingual OCR","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2207.10273","title":"Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context","created":"2022-07-21","cited_by_count":18,"area":null},{"id":"2110.12663","title":"Industrial Scene Text Detection with Refined Feature-attentive Network","created":"2021-10-25","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":"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":"2104.01552","title":"Scene Text Retrieval via Joint Text Detection and Similarity Learning","created":"2021-04-04","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":"2108.01343","title":"I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection","created":"2021-08-03","cited_by_count":14,"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":"2405.06706","title":"Exploring the Capabilities of Large Multimodal Models on Dense Text","created":"2024-05-09","cited_by_count":14,"area":"mllm"},{"id":"2206.13381","title":"TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask","created":"2022-06-27","cited_by_count":13,"area":null},{"id":"2207.04675","title":"COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts","created":"2022-07-11","cited_by_count":13,"area":null},{"id":"2306.12106","title":"ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining","created":"2023-06-21","cited_by_count":12,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","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":"2112.06104","title":"Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection","created":"2021-12-12","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":"2308.10408","title":"Turning a CLIP Model into a Scene Text Spotter","created":"2023-08-21","cited_by_count":9,"area":null},{"id":"2312.05286","title":"Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors","created":"2023-12-08","cited_by_count":9,"area":null},{"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":"2204.05535","title":"Open-set Text Recognition via Character-Context Decoupling","created":"2022-04-12","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":"2412.01137","title":"TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2108.10840","title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","created":"2021-08-24","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":"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":"2505.20298","title":"MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2201.03180","title":"Transfer Learning for Scene Text Recognition in Indian Languages","created":"2022-01-10","cited_by_count":6,"area":null},{"id":"2212.02340","title":"CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2302.10641","title":"A3S: Adversarial learning of semantic representations for Scene-Text Spotting","created":"2023-02-21","cited_by_count":6,"area":null},{"id":"2308.02905","title":"FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework","created":"2023-08-05","cited_by_count":6,"area":null},{"id":"2405.12669","title":"A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges","created":"2024-05-21","cited_by_count":6,"area":null},{"id":"2408.00441","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2103.04635","title":"FEDS -- Filtered Edit Distance Surrogate","created":"2021-03-08","cited_by_count":5,"area":null},{"id":"2201.06648","title":"OmniPrint: A Configurable Printed Character Synthesizer","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2209.02397","title":"A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data","created":"2022-09-06","cited_by_count":5,"area":null},{"id":"2211.03256","title":"On Web-based Visual Corpus Construction for Visual Document Understanding","created":"2022-11-07","cited_by_count":5,"area":null},{"id":"2212.04116","title":"OCR-RTPS: An OCR-based real-time positioning system for the valet parking","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2304.10097","title":"Scene Style Text Editing","created":"2023-04-20","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":"2409.16820","title":"Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2511.15059","title":"Evaluating Multimodal Large Language Models on Vertically Written Japanese Text","created":"2025-11-19","cited_by_count":4,"area":"mllm"},{"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":"2312.10806","title":"Cross-Lingual Learning in Multilingual Scene Text Recognition","created":"2023-12-17","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":"2408.05706","title":"Decoder Pre-Training with only Text for Scene Text Recognition","created":"2024-08-11","cited_by_count":3,"area":null},{"id":"2411.10261","title":"Partial Scene Text Retrieval","created":"2024-11-15","cited_by_count":3,"area":null},{"id":"2505.15649","title":"The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2209.00859","title":"Vision-Language Adaptive Mutual Decoder for OOV-STR","created":"2022-09-02","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":"2306.14269","title":"Weakly Supervised Scene Text Generation for Low-resource Languages","created":"2023-06-25","cited_by_count":2,"area":null},{"id":"2307.13310","title":"CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2309.02356","title":"STEP -- Towards Structured Scene-Text Spotting","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2405.11437","title":"The First Swahili Language Scene Text Detection and Recognition Dataset","created":"2024-05-19","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":"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":"2603.15409","title":"SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2104.08045","title":"TeLCoS: OnDevice Text Localization with Clustering of Script","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2111.11718","title":"StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks","created":"2021-11-23","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":"2201.03185","title":"Towards Boosting the Accuracy of Non-Latin Scene Text Recognition","created":"2022-01-10","cited_by_count":1,"area":null}],"next_cursor":"100"}