{"total":214,"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":"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":"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":"2205.00159","title":"SVTR: Scene Text Recognition with a Single Visual Model","created":"2022-04-30","cited_by_count":88,"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":"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":"2306.10804","title":"Conditional Text Image Generation with Diffusion Models","created":"2023-06-19","cited_by_count":58,"area":"diffusion"},{"id":"2104.07787","title":"Rethinking Text Line Recognition Models","created":"2021-04-15","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":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45,"area":null},{"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":"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":"2106.15368","title":"Text Prior Guided Scene Text Image Super-resolution","created":"2021-06-29","cited_by_count":37,"area":null},{"id":"2212.01982","title":"Exploring Stroke-Level Modifications for Scene Text Editing","created":"2022-12-05","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":"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":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27,"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":"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":"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":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"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":"2405.04377","title":"Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing","created":"2024-05-07","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":"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":"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":"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":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","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},{"id":"2310.04999","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","created":"2023-10-08","cited_by_count":14,"area":"distill"},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2401.10222","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2512.21095","title":"UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters","created":"2025-12-24","cited_by_count":13,"area":null},{"id":"2107.12081","title":"Towards the Unseen: Iterative Text Recognition by Distilling from Errors","created":"2021-07-26","cited_by_count":12,"area":null},{"id":"2201.09390","title":"AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks","created":"2022-01-23","cited_by_count":12,"area":null},{"id":"2203.05179","title":"Towards Open-Set Text Recognition via Label-to-Prototype Learning","created":"2022-03-10","cited_by_count":12,"area":null},{"id":"2104.04437","title":"Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam","created":"2021-04-09","cited_by_count":11,"area":null},{"id":"2105.03906","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","created":"2021-05-09","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":"2407.12317","title":"Out of Length Text Recognition with Sub-String Matching","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2204.03776","title":"TorMentor: Deterministic dynamic-path, data augmentations with fractals","created":"2022-04-07","cited_by_count":10,"area":null},{"id":"2207.10256","title":"SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition","created":"2022-07-21","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":"2411.17332","title":"On the Generalization of Handwritten Text Recognition Models","created":"2024-11-26","cited_by_count":10,"area":null},{"id":"2204.12743","title":"Self-Supervised Text Erasing with Controllable Image Synthesis","created":"2022-04-27","cited_by_count":9,"area":null},{"id":"2211.04963","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2305.05322","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2204.05535","title":"Open-set Text Recognition via Character-Context Decoupling","created":"2022-04-12","cited_by_count":8,"area":null},{"id":"2207.14807","title":"PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2308.08806","title":"Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach","created":"2023-08-17","cited_by_count":8,"area":"distill"},{"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":"2401.14832","title":"Text Image Inpainting via Global Structure-Guided Diffusion Models","created":"2024-01-26","cited_by_count":8,"area":"diffusion"},{"id":"2405.05841","title":"Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2408.02253","title":"Advancing Post-OCR Correction: A Comparative Study of Synthetic Data","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2412.01137","title":"TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2412.13871","title":"LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer","created":"2024-12-18","cited_by_count":8,"area":"mllm"},{"id":"2108.10840","title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","created":"2021-08-24","cited_by_count":7,"area":null},{"id":"2204.07714","title":"Pushing the Performance Limit of Scene Text Recognizer without Human Annotation","created":"2022-04-16","cited_by_count":7,"area":null},{"id":"2306.16707","title":"DiffusionSTR: Diffusion Model for Scene Text Recognition","created":"2023-06-29","cited_by_count":7,"area":"diffusion"},{"id":"2307.13244","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","created":"2023-07-25","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":"2503.13385","title":"Scale Efficient Training for Large Datasets","created":"2025-03-17","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":"2509.05146","title":"PRIM: Towards Practical In-Image Multilingual Machine Translation","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2106.02859","title":"Convolutional Neural Networks with Gated Recurrent Connections","created":"2021-06-05","cited_by_count":6,"area":null},{"id":"2106.06960","title":"Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2021-06-13","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":"2308.00508","title":"Relational Contrastive Learning for Scene Text Recognition","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2308.02905","title":"FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework","created":"2023-08-05","cited_by_count":6,"area":null},{"id":"2503.04058","title":"EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models","created":"2025-03-06","cited_by_count":6,"area":"mllm"},{"id":"2102.10884","title":"Revisiting Classification Perspective on Scene Text Recognition","created":"2021-02-22","cited_by_count":5,"area":null},{"id":"2105.06229","title":"Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition","created":"2021-05-13","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":"2106.05920","title":"Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter","created":"2021-06-10","cited_by_count":5,"area":null}],"next_cursor":"100"}