{"total":396,"rows":[{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"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":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279,"area":null},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229,"area":"diffusion"},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194,"area":null},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186,"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":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149,"area":null},{"id":"2108.09661","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","created":"2021-08-22","cited_by_count":97,"area":"mllm"},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"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":"2302.02041","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","created":"2023-02-04","cited_by_count":94,"area":null},{"id":"2410.16261","title":"Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance","created":"2024-10-21","cited_by_count":94,"area":"mllm"},{"id":"2205.00159","title":"SVTR: Scene Text Recognition with a Single Visual Model","created":"2022-04-30","cited_by_count":88,"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":"2105.08582","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","created":"2021-05-18","cited_by_count":81,"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":"2209.01206","title":"Transformers in Remote Sensing: A Survey","created":"2022-09-02","cited_by_count":61,"area":null},{"id":"2312.04884","title":"UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models","created":"2023-12-08","cited_by_count":59,"area":"diffusion"},{"id":"2206.07835","title":"Disentangling visual and written concepts in CLIP","created":"2022-06-15","cited_by_count":58,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58,"area":"diffusion"},{"id":"2501.05952","title":"Scalable Vision Language Model Training via High Quality Data Curation","created":"2025-01-10","cited_by_count":55,"area":"mllm"},{"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":"2106.08385","title":"TextStyleBrush: Transfer of Text Aesthetics from a Single Example","created":"2021-06-15","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":"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":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45,"area":null},{"id":"2304.05568","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","created":"2023-04-12","cited_by_count":45,"area":"diffusion"},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45,"area":null},{"id":"2410.10133","title":"TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control","created":"2024-10-14","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":"2107.09313","title":"SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models","created":"2021-07-20","cited_by_count":43,"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":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","cited_by_count":41,"area":null},{"id":"2312.12232","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","created":"2023-12-19","cited_by_count":41,"area":"diffusion"},{"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":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40,"area":null},{"id":"2106.15368","title":"Text Prior Guided Scene Text Image Super-resolution","created":"2021-06-29","cited_by_count":37,"area":null},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37,"area":"mllm"},{"id":"2111.11011","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","created":"2021-11-22","cited_by_count":36,"area":null},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36,"area":null},{"id":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34,"area":null},{"id":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","cited_by_count":34,"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":"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":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2105.04286","title":"Primitive Representation Learning for Scene Text Recognition","created":"2021-05-10","cited_by_count":28,"area":null},{"id":"2112.08171","title":"Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution","created":"2021-12-13","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":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27,"area":null},{"id":"2502.07870","title":"TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation","created":"2025-02-11","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":"2202.11456","title":"SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text","created":"2022-02-23","cited_by_count":26,"area":null},{"id":"2112.12916","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","created":"2021-12-24","cited_by_count":25,"area":null},{"id":"2203.03382","title":"Self-supervised Implicit Glyph Attention for Text Recognition","created":"2022-03-07","cited_by_count":25,"area":null},{"id":"2107.12090","title":"Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition","created":"2021-07-26","cited_by_count":24,"area":null},{"id":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24,"area":null},{"id":"2411.15858","title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","created":"2024-11-24","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":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23,"area":null},{"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":"2203.10492","title":"SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization","created":"2022-03-20","cited_by_count":21,"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":"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":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2504.21682","title":"Visual Text Processing: A Comprehensive Review and Unified Evaluation","created":"2025-04-30","cited_by_count":19,"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":"2305.05140","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","created":"2023-05-09","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":"2405.14701","title":"DreamText: High Fidelity Scene Text Synthesis","created":"2024-05-23","cited_by_count":18,"area":null},{"id":"2107.12087","title":"Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation","created":"2021-07-26","cited_by_count":17,"area":"distill"},{"id":"2401.17851","title":"Instruction-Guided Scene Text Recognition","created":"2024-01-31","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":"2203.04814","title":"Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2205.03873","title":"Multimodal Semi-Supervised Learning for Text Recognition","created":"2022-05-08","cited_by_count":16,"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":"2410.10168","title":"First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending","created":"2024-10-14","cited_by_count":16,"area":"diffusion"},{"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":"2207.14801","title":"Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach","created":"2022-07-29","cited_by_count":15,"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":"2302.10414","title":"Improving Scene Text Image Super-resolution via Dual Prior Modulation Network","created":"2023-02-21","cited_by_count":15,"area":null},{"id":"2311.09759","title":"Scene Text Image Super-resolution based on Text-conditional Diffusion Models","created":"2023-11-16","cited_by_count":15,"area":"diffusion"},{"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":"2209.00641","title":"Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition","created":"2022-08-31","cited_by_count":14,"area":null}],"next_cursor":"100"}