{"total":162,"rows":[{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"area":"mllm"},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217,"area":"mllm"},{"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":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173,"area":"mllm"},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"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":"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":"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":"2104.10442","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","created":"2021-04-21","cited_by_count":80,"area":null},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74,"area":"mllm"},{"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":"2209.01206","title":"Transformers in Remote Sensing: A Survey","created":"2022-09-02","cited_by_count":61,"area":null},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53,"area":null},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"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":"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":"2104.07787","title":"Rethinking Text Line Recognition Models","created":"2021-04-15","cited_by_count":45,"area":null},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45,"area":null},{"id":"2207.00193","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","created":"2022-07-01","cited_by_count":45,"area":null},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45,"area":null},{"id":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","cited_by_count":41,"area":null},{"id":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35,"area":"mllm"},{"id":"2208.03364","title":"GLASS: Global to Local Attention for Scene-Text Spotting","created":"2022-08-05","cited_by_count":34,"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":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2203.03911","title":"Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting","created":"2022-03-08","cited_by_count":27,"area":"mllm"},{"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":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2505.13077","title":"Advancing Sequential Numerical Prediction in Autoregressive Models","created":"2025-05-19","cited_by_count":26,"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":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2503.14140","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","created":"2025-03-18","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":"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":"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":"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":"2503.02304","title":"A Token-level Text Image Foundation Model for Document Understanding","created":"2025-03-04","cited_by_count":14,"area":"mllm"},{"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":"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":"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":"2209.03016","title":"Text Growing on Leaf","created":"2022-09-07","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":"2405.21013","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","created":"2024-05-31","cited_by_count":11,"area":"mllm"},{"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":"2207.01342","title":"Explore Faster Localization Learning For Scene Text Detection","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2402.13643","title":"Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition","created":"2024-02-21","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":"2207.11469","title":"Progressive Scene Text Erasing with Self-Supervision","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2308.03729","title":"TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models","created":"2023-08-07","cited_by_count":9,"area":"mllm"},{"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":"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":"2110.10405","title":"ARTS: Eliminating Inconsistency between Text Detection and Recognition with Auto-Rectification Text Spotter","created":"2021-10-20","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":"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":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","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":"2202.11221","title":"Arbitrary Shape Text Detection using Transformers","created":"2022-02-22","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":"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":"2506.09993","title":"Text-Aware Image Restoration with Diffusion Models","created":"2025-06-11","cited_by_count":6,"area":"diffusion"},{"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":"2105.08383","title":"I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition","created":"2021-05-18","cited_by_count":5,"area":null},{"id":"2205.08257","title":"Detection Masking for Improved OCR on Noisy Documents","created":"2022-05-17","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":"2308.10531","title":"SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression","created":"2023-08-21","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":"2408.00106","title":"WAS: Dataset and Methods for Artistic Text Segmentation","created":"2024-07-31","cited_by_count":5,"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":"2303.10848","title":"Weakly-Supervised Text Instance Segmentation","created":"2023-03-20","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":"2407.17020","title":"EAFormer: Scene Text Segmentation with Edge-Aware Transformers","created":"2024-07-24","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":"2511.05818","title":"LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2210.07423","title":"Task Grouping for Multilingual Text Recognition","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2307.04245","title":"A Novel Pipeline for Improving Optical Character Recognition through Post-processing Using Natural Language Processing","created":"2023-07-09","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":"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":"2311.10793","title":"Traffic Sign Interpretation in Real Road Scene","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2407.02842","title":"MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis","created":"2024-07-03","cited_by_count":3,"area":"mllm"},{"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":"2411.10261","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":"2506.03799","title":"ConText: Driving In-context Learning for Text Removal and Segmentation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2204.00298","title":"Unitail: Detecting, Reading, and Matching in Retail Scene","created":"2022-04-01","cited_by_count":2,"area":null},{"id":"2205.08565","title":"Text Detection & Recognition in the Wild for Robot Localization","created":"2022-05-17","cited_by_count":2,"area":null}],"next_cursor":"100"}