{"total":94,"rows":[{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229,"area":"diffusion"},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180,"area":null},{"id":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95,"area":"mllm"},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88,"area":"diffusion"},{"id":"2403.19128","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","created":"2024-03-28","cited_by_count":74,"area":null},{"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":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39,"area":null},{"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":"2205.05320","title":"Arbitrary Shape Text Detection via Boundary Transformer","created":"2022-05-11","cited_by_count":28,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2207.07563","title":"QSAN: A Near-term Achievable Quantum Self-Attention Network","created":"2022-07-14","cited_by_count":25,"area":null},{"id":"2502.16161","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","created":"2025-02-22","cited_by_count":23,"area":"lr"},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22,"area":null},{"id":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"id":"2305.05095","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","created":"2023-05-08","cited_by_count":19,"area":null},{"id":"2601.00051","title":"TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model","created":"2025-12-31","cited_by_count":16,"area":"wm"},{"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":"2205.15469","title":"GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector","created":"2022-05-30","cited_by_count":11,"area":null},{"id":"2209.03016","title":"Text Growing on Leaf","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2403.00303","title":"ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting","created":"2024-03-01","cited_by_count":10,"area":null},{"id":"2604.03723","title":"SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation","created":"2026-04-04","cited_by_count":10,"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":"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":"2502.16586","title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","created":"2025-02-23","cited_by_count":9,"area":"mllm"},{"id":"2306.15142","title":"LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network","created":"2023-06-27","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":"2404.08965","title":"Seeing Text in the Dark: Algorithm and Benchmark","created":"2024-04-13","cited_by_count":8,"area":null},{"id":"2503.20698","title":"MMMORRF: Multimodal Multilingual Modularized Reciprocal Rank Fusion","created":"2025-03-26","cited_by_count":8,"area":"mllm"},{"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":"2312.01938","title":"DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text","created":"2023-11-29","cited_by_count":7,"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":"2403.02336","title":"Brand Visibility in Packaging: A Deep Learning Approach for Logo Detection, Saliency-Map Prediction, and Logo Placement Analysis","created":"2024-03-04","cited_by_count":6,"area":null},{"id":"2506.23729","title":"Proteus-ID: ID-Consistent and Motion-Coherent Video Customization","created":"2025-06-30","cited_by_count":6,"area":null},{"id":"2406.03916","title":"ArMeme: Propagandistic Content in Arabic Memes","created":"2024-06-06","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":"2308.12817","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","created":"2023-08-23","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":"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":"2601.17340","title":"TEXTS-Diff: TEXTS-Aware Diffusion Model for Real-World Text Image Super-Resolution","created":"2026-01-24","cited_by_count":4,"area":"diffusion"},{"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":"2411.02794","title":"Real-Time Text Detection with Similar Mask in Traffic, Industrial, and Natural Scenes","created":"2024-11-05","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":"2307.13310","title":"CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer","created":"2023-07-25","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":"2401.05167","title":"Watermark Text Pattern Spotting in Document Images","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2405.07481","title":"Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2405.19765","title":"Towards Unified Multi-granularity Text Detection with Interactive Attention","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2406.15485","title":"SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line Detection","created":"2024-06-17","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":"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":"2503.15887","title":"DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2512.06657","title":"TextMamba: Scene Text Detector with Mamba","created":"2025-12-07","cited_by_count":2,"area":"ssm"},{"id":"2304.13240","title":"Structure Diagram Recognition in Financial Announcements","created":"2023-04-26","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":"2403.11107","title":"Self-supervised co-salient object detection via feature correspondence at multiple scales","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2406.16307","title":"Artistic-style text detector and a new Movie-Poster dataset","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2412.01601","title":"Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2507.12938","title":"Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion","created":"2025-07-17","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":"2510.02543","title":"Exploring OCR-augmented Generation for Bilingual VQA","created":"2025-10-02","cited_by_count":1,"area":"mllm"},{"id":"2604.11376","title":"From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2208.09878","title":"DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection","created":"2022-08-21","cited_by_count":0,"area":null},{"id":"2211.13984","title":"Aggregated Text Transformer for Scene Text Detection","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2308.02369","title":"Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition","created":"2023-08-04","cited_by_count":0,"area":null},{"id":"2312.11153","title":"Research on Multilingual Natural Scene Text Detection Algorithm","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2401.09997","title":"BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2401.10017","title":"Text Region Multiple Information Perception Network for Scene Text Detection","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2402.11540","title":"CPN: Complementary Proposal Network for Unconstrained Text Detection","created":"2024-02-18","cited_by_count":0,"area":null},{"id":"2404.00852","title":"Ensemble Learning for Vietnamese Scene Text Spotting in Urban Environments","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2404.19652","title":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2405.19194","title":"LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2407.10709","title":"Detecting Omissions in Geographic Maps through Computer Vision","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2409.16827","title":"Focus Entirety and Perceive Environment for Arbitrary-Shaped Text Detection","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2502.05277","title":"Invizo: Arabic Handwritten Document Optical Character Recognition Solution","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2503.06472","title":"CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model","created":"2025-03-09","cited_by_count":0,"area":"mllm"},{"id":"2505.06038","title":"Document Image Rectification Bases on Self-Adaptive Multitask Fusion","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2507.20188","title":"SAViL-Det: Semantic-Aware Vision-Language Model for Multi-Script Text Detection","created":"2025-07-27","cited_by_count":0,"area":"mllm"},{"id":"2508.02372","title":"TRUDI and TITUS: A Multi-Perspective Dataset and A Three-Stage Recognition System for Transportation Unit Identification","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2510.02787","title":"OTR: Synthesizing Overlay Text Dataset for Text Removal","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.13303","title":"Automated document processing system for government agencies using DBNET++ and BART models","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2510.15557","title":"ClapperText: A Benchmark for Text Recognition in Low-Resource Archival Documents","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.11691","title":"Text images processing system using artificial intelligence models","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.11248","title":"Language-Agnostic Visual Embeddings for Cross-Script Handwriting Retrieval","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2601.18098","title":"Text-Pass Filter: An Efficient Scene Text Detector","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.22946","title":"Caption Generation for Dongba Paintings via Prompt Learning and Semantic Fusion","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.25168","title":"ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.08902","title":"DAPE: Dynamic Non-uniform Alignment and Progressive Detail Enhancement Techniques for Improving the Performance of Efficient Visual Language Models","created":"2026-05-09","cited_by_count":0,"area":"mllm"},{"id":"2605.18173","title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.23486","title":"From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.27393","title":"AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2607.27902","title":"One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.04392","title":"FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}