{"total":119,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"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":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94,"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":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74,"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":"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":"2105.00405","title":"PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text","created":"2021-05-02","cited_by_count":65,"area":null},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65,"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":"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":"2104.05458","title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","created":"2021-04-12","cited_by_count":49,"area":null},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47,"area":null},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","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":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2104.01070","title":"MOST: A Multi-Oriented Scene Text Detector with Localization Refinement","created":"2021-04-02","cited_by_count":33,"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":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"area":null},{"id":"2205.05320","title":"Arbitrary Shape Text Detection via Boundary Transformer","created":"2022-05-11","cited_by_count":28,"area":null},{"id":"2105.02184","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27,"area":null},{"id":"2110.12826","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","created":"2021-10-25","cited_by_count":26,"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":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","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":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18,"area":"mllm"},{"id":"2203.06410","title":"Kernel Proposal Network for Arbitrary Shape Text Detection","created":"2022-03-12","cited_by_count":17,"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":"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":"2107.05945","title":"CentripetalText: An Efficient Text Instance Representation for Scene Text Detection","created":"2021-07-13","cited_by_count":13,"area":null},{"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":"2209.03016","title":"Text Growing on Leaf","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2111.04987","title":"Video Text Tracking With a Spatio-Temporal Complementary Model","created":"2021-11-09","cited_by_count":10,"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":"2111.02394","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","created":"2021-11-03","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":"2401.03637","title":"Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling","created":"2024-01-08","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":"2106.12720","title":"All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection","created":"2021-06-24","cited_by_count":7,"area":null},{"id":"2203.05122","title":"DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting","created":"2022-03-10","cited_by_count":7,"area":null},{"id":"2209.03014","title":"Zoom Text Detector","created":"2022-09-07","cited_by_count":7,"area":null},{"id":"2412.15523","title":"InstructOCR: Instruction Boosting Scene Text Spotting","created":"2024-12-20","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":"2202.11221","title":"Arbitrary Shape Text Detection using Transformers","created":"2022-02-22","cited_by_count":6,"area":null},{"id":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","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":"2506.09993","title":"Text-Aware Image Restoration with Diffusion Models","created":"2025-06-11","cited_by_count":6,"area":"diffusion"},{"id":"2101.00604","title":"Privacy-sensitive Objects Pixelation for Live Video Streaming","created":"2021-01-03","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":"2210.07903","title":"Text Detection Forgot About Document OCR","created":"2022-10-14","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":"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":"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":"2409.16820","title":"Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2302.01540","title":"DEVICE: Depth and Visual Concepts Aware Transformer for OCR-based Image Captioning","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2407.19507","title":"WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting","created":"2024-07-28","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":"2504.04001","title":"Edge Approximation Text Detector","created":"2025-04-05","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":"2508.18641","title":"Clustering-based Feature Representation Learning for Oracle Bone Inscriptions Detection","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2203.05251","title":"Real-time Scene Text Detection Based on Global Level and Word Level Features","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2206.02628","title":"HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2212.00377","title":"Domain Adaptive Scene Text Detection via Subcategorization","created":"2022-12-01","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":"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":"2405.11437","title":"The First Swahili Language Scene Text Detection and Recognition Dataset","created":"2024-05-19","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":"2408.14998","title":"FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting","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":"2503.18641","title":"From Fragment to One Piece: A Survey on AI-Driven Graphic Design","created":"2025-03-24","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":"2103.09179","title":"Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection","created":"2021-03-16","cited_by_count":1,"area":null},{"id":"2106.05542","title":"DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents","created":"2021-06-10","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":"2202.06565","title":"Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2207.07253","title":"Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and Recognition","created":"2022-07-15","cited_by_count":1,"area":null},{"id":"2310.00917","title":"Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2312.13778","title":"Progressive Evolution from Single-Point to Polygon for Scene Text","created":"2023-12-21","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":"2404.13779","title":"Automated Text Mining of Experimental Methodologies from Biomedical Literature","created":"2024-04-21","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":"2104.00297","title":"Arbitrary-Shaped Text Detection withAdaptive Text Region Representation","created":"2021-04-01","cited_by_count":0,"area":null},{"id":"2105.05455","title":"MT: Multi-Perspective Feature Learning Network for Scene Text Detection","created":"2021-05-12","cited_by_count":0,"area":null},{"id":"2105.12789","title":"RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection","created":"2021-05-26","cited_by_count":0,"area":null},{"id":"2107.06129","title":"Bidirectional Regression for Arbitrary-Shaped Text Detection","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2109.01034","title":"Scene Text recognition with Full Normalization","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2111.05671","title":"Pre-trained Transformer-Based Approach for Arabic Question Answering : A Comparative Study","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2111.14340","title":"Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2201.04866","title":"Weakly Supervised Scene Text Detection using Deep Reinforcement Learning","created":"2022-01-13","cited_by_count":0,"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":"2211.11350","title":"Rooms with Text: A Dataset for Overlaying Text Detection","created":"2022-11-21","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":"2301.03164","title":"Cursive Caption Text Detection in Videos","created":"2023-01-09","cited_by_count":0,"area":null}],"next_cursor":"100"}