{"total":170,"rows":[{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"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":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171,"area":null},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"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":"2203.02431","title":"Rethinking Efficient Lane Detection via Curve Modeling","created":"2022-03-04","cited_by_count":88,"area":null},{"id":"2308.16477","title":"PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction","created":"2023-08-31","cited_by_count":85,"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":"2306.09700","title":"End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve","created":"2023-06-16","cited_by_count":82,"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":"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":"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":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45,"area":null},{"id":"2107.05214","title":"Split, embed and merge: An accurate table structure recognizer","created":"2021-07-12","cited_by_count":42,"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":"2211.10578","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","created":"2022-11-19","cited_by_count":40,"area":null},{"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":"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":"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":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25,"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":"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":"2203.10539","title":"End-to-End Video Text Spotting with Transformer","created":"2022-03-20","cited_by_count":22,"area":null},{"id":"2407.14138","title":"Visual Text Generation in the Wild","created":"2024-07-19","cited_by_count":22,"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":"2309.01131","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","created":"2023-09-03","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":"2104.01552","title":"Scene Text Retrieval via Joint Text Detection and Similarity Learning","created":"2021-04-04","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":"2111.09162","title":"It's About Time: Analog Clock Reading in the Wild","created":"2021-11-17","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":"2305.01443","title":"Scalable Mask Annotation for Video Text Spotting","created":"2023-05-02","cited_by_count":13,"area":null},{"id":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","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":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12,"area":null},{"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":"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":"2209.06717","title":"Out-of-Vocabulary Challenge Report","created":"2022-09-14","cited_by_count":11,"area":null},{"id":"2405.15196","title":"DisC-GS: Discontinuity-aware Gaussian Splatting","created":"2024-05-24","cited_by_count":11,"area":null},{"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":"2207.01342","title":"Explore Faster Localization Learning For Scene Text Detection","created":"2022-07-04","cited_by_count":10,"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":"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":"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":"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":"2507.15085","title":"OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities","created":"2025-07-20","cited_by_count":9,"area":null},{"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":"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":"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":"2209.03014","title":"Zoom Text Detector","created":"2022-09-07","cited_by_count":7,"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":"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":"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":"2603.23885","title":"Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training","created":"2026-03-25","cited_by_count":7,"area":"mllm"},{"id":"2101.11782","title":"Object Detection Made Simpler by Eliminating Heuristic NMS","created":"2021-01-28","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":"2207.12955","title":"Contextual Text Block Detection towards Scene Text Understanding","created":"2022-07-26","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":"2303.09174","title":"Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation","created":"2023-03-16","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":"2106.05920","title":"Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter","created":"2021-06-10","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":"2212.05525","title":"Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images","created":"2022-12-11","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":"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":"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":"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":"2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2304.11966","title":"ICDAR 2023 Competition on Reading the Seal Title","created":"2023-04-24","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":"2207.14477","title":"FCSN: Global Context Aware Segmentation by Learning the Fourier Coefficients of Objects in Medical Images","created":"2022-07-29","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}],"next_cursor":"100"}