{"total":82,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197,"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":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80,"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":"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":"2109.04145","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","created":"2021-09-09","cited_by_count":41,"area":null},{"id":"2207.10040","title":"Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model","created":"2022-07-20","cited_by_count":37,"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":"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":"2307.10603","title":"Physics-Driven Turbulence Image Restoration with Stochastic Refinement","created":"2023-07-20","cited_by_count":24,"area":null},{"id":"2109.03426","title":"Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection","created":"2021-09-08","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":"2103.15992","title":"A Multiplexed Network for End-to-End, Multilingual OCR","created":"2021-03-29","cited_by_count":18,"area":null},{"id":"2203.06410","title":"Kernel Proposal Network for Arbitrary Shape Text Detection","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2208.12419","title":"Arbitrary Shape Text Detection via Segmentation with Probability Maps","created":"2022-08-26","cited_by_count":15,"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":"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":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12,"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":"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":"2207.08417","title":"Real-time End-to-End Video Text Spotter with Contrastive Representation Learning","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2109.03794","title":"Digitize-PID: Automatic Digitization of Piping and Instrumentation Diagrams","created":"2021-09-08","cited_by_count":6,"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":"2207.12955","title":"Contextual Text Block Detection towards Scene Text Understanding","created":"2022-07-26","cited_by_count":6,"area":null},{"id":"2103.00785","title":"Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links","created":"2021-03-01","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":"2109.03451","title":"Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2109.11243","title":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2112.07513","title":"CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2112.14976","title":"Contrastive Learning of Semantic and Visual Representations for Text Tracking","created":"2021-12-30","cited_by_count":4,"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":"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":"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":"2508.18641","title":"Clustering-based Feature Representation Learning for Oracle Bone Inscriptions Detection","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2105.00333","title":"AI-enabled Efficient and Safe Food Supply Chain","created":"2021-05-01","cited_by_count":2,"area":null},{"id":"2108.06881","title":"Text-Aware Single Image Specular Highlight Removal","created":"2021-08-16","cited_by_count":2,"area":null},{"id":"2111.00629","title":"Distantly Supervised Semantic Text Detection and Recognition for Broadcast Sports Videos Understanding","created":"2021-10-31","cited_by_count":2,"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":"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":"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":"2504.03621","title":"PILOT: A Promptable Interleaved Layout-aware OCR Transformer","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2601.14490","title":"GutenOCR: A Grounded Vision-Language Front-End for Documents","created":"2026-01-20","cited_by_count":2,"area":null},{"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":"2210.04244","title":"Text detection and recognition based on a lensless imaging system","created":"2022-10-09","cited_by_count":1,"area":null},{"id":"2301.02445","title":"IMKGA-SM: Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling","created":"2023-01-06","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":"2406.16307","title":"Artistic-style text detector and a new Movie-Poster dataset","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2407.08993","title":"Task-driven single-image super-resolution reconstruction of document scans","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2503.03104","title":"RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognition","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2101.01310","title":"Research on Fast Text Recognition Method for Financial Ticket Image","created":"2021-01-05","cited_by_count":0,"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":"2106.05611","title":"Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition","created":"2021-06-10","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":"2206.02343","title":"Contrastive Graph Multimodal Model for Text Classification in Videos","created":"2022-06-06","cited_by_count":0,"area":null},{"id":"2210.08266","title":"MenuAI: Restaurant Food Recommendation System via a Transformer-based Deep Learning Model","created":"2022-10-15","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":"2211.15999","title":"Impact of Automatic Image Classification and Blind Deconvolution in Improving Text Detection Performance of the CRAFT Algorithm","created":"2022-11-29","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},{"id":"2309.09800","title":"AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and Classification","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2310.11650","title":"VKIE: The Application of Key Information Extraction on Video Text","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2311.09256","title":"Reading Between the Mud: A Challenging Motorcycle Racer Number Dataset","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2311.13222","title":"Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approach","created":"2023-11-22","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":"2312.15690","title":"Word length-aware text spotting: Enhancing detection and recognition in dense text image","created":"2023-12-25","cited_by_count":0,"area":null},{"id":"2401.03694","title":"GloTSFormer: Global Video Text Spotting Transformer","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2402.08025","title":"Beyond the Mud: Datasets and Benchmarks for Computer Vision in Off-Road Racing","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2403.11536","title":"OCR is All you need: Importing Multi-Modality into Image-based Defect Detection System","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2404.05183","title":"Progressive Alignment with VLM-LLM Feature to Augment Defect Classification for the ASE Dataset","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2503.15639","title":"A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition","created":"2025-03-19","cited_by_count":0,"area":null}],"next_cursor":null}