{"total":70,"rows":[{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"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":"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":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66,"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":"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":"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":"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":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27,"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":"2305.04183","title":"OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese","created":"2023-05-07","cited_by_count":20,"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":"2506.05551","title":"When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding","created":"2025-06-05","cited_by_count":12,"area":"mllm"},{"id":"2408.00355","title":"DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training","created":"2024-08-01","cited_by_count":11,"area":null},{"id":"2412.10159","title":"Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance","created":"2024-12-13","cited_by_count":11,"area":null},{"id":"2505.22810","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2307.07662","title":"MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression","created":"2023-07-14","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":"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":"2306.17059","title":"The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps","created":"2023-06-29","cited_by_count":8,"area":null},{"id":"2404.18397","title":"ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images","created":"2024-04-29","cited_by_count":8,"area":null},{"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":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2404.10652","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images","created":"2024-04-16","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":"2506.15010","title":"Hyper-Local Deformable Transformers for Text Spotting on Historical Maps","created":"2025-06-17","cited_by_count":7,"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":"2308.10531","title":"SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression","created":"2023-08-21","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":"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":"2308.13173","title":"DISGO: Automatic End-to-End Evaluation for Scene Text OCR","created":"2023-08-25","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":"2309.12382","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","created":"2023-09-21","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":"2309.00410","title":"Selective Scene Text Removal","created":"2023-09-01","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":"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":"2408.14998","title":"FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2411.16713","title":"Conditional Text-to-Image Generation with Reference Guidance","created":"2024-11-22","cited_by_count":2,"area":"diffusion"},{"id":"2504.09966","title":"SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2507.05805","title":"DREAM: Document Reconstruction via End-to-end Autoregressive Model","created":"2025-07-08","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":"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":"2208.06079","title":"Character decomposition to resolve class imbalance problem in Hangul OCR","created":"2022-08-12","cited_by_count":1,"area":null},{"id":"2310.00546","title":"Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation","created":"2023-10-01","cited_by_count":1,"area":"diffusion"},{"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":"2402.17134","title":"Efficiently Leveraging Linguistic Priors for Scene Text Spotting","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2512.22218","title":"Towards Signboard-Oriented Visual Question Answering: ViSignVQA Dataset, Method and Benchmark","created":"2025-12-22","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":"2208.09878","title":"DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection","created":"2022-08-21","cited_by_count":0,"area":null},{"id":"2308.16404","title":"Deformation Robust Text Spotting with Geometric Prior","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2309.11248","title":"Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text","created":"2023-09-20","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":"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":"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":"2405.09942","title":"FPDIoU Loss: A Loss Function for Efficient Bounding Box Regression of Rotated Object Detection","created":"2024-05-16","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":"2410.14132","title":"ViConsFormer: Constituting Meaningful Phrases of Scene Texts using Transformer-based Method in Vietnamese Text-based Visual Question Answering","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2411.01139","title":"HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction","created":"2024-11-02","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},{"id":"2506.07112","title":"EdgeSpotter: Multi-Scale Dense Text Spotting for Industrial Panel Monitoring","created":"2025-06-08","cited_by_count":0,"area":null},{"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":"2606.07161","title":"TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.28676","title":"Automated pipeline for herbarium label digitization","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.07081","title":"SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text Spotting","created":"2026-09-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}