Scene Text Recognition

Ask about this topic

Overview

Scene text recognition studies how to locate and transcribe writing in photographs and video, where text may be curved, rotated, blurred, or mixed with clutter. Systems commonly combine text detection with CNN or Transformer recognizers, using either CTC or autoregressive decoding; newer work also uses vision-language models, synthetic data, self-supervision, and script-aware expert routing. Benchmarks increasingly test multilingual and language-specific reading, artistic text, long inputs, video, and degraded or misleading scenes, not just standard English word images. A central challenge is balancing visual character evidence with linguistic context: context can help with ambiguity but can also cause models to replace rare or clearly visible text with more plausible words, while low-resource scripts and difficult real-world conditions remain weaknesses.

Latest papers

CardsList

29 papers2 papers in the last four weeks, down 60% on the four weeks before. 0.0% of all new papers.

  1. ArabGeoText: Tool-Augmented Vision-Language Models for Arabic Geospatial Text Spotting

    Nov 2, 2026Yakoub Bazi, Sarah Alsaleh, Mohamad M. Al Rahhal +2Scene Text RecognitionTool Use in VLMs

    Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia · Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh 11543, Saudi Arabia

  2. FlexReader: Towards Adaptive Decoding Paths for Efficient Arbitrary-Length Scene Text Recognition

    Oct 30, 2026Zhibin Ma, Pengwen Dai, Zhigang Yao +3Scene Text RecognitionAdaptive Inference

    Shenzhen Campus of Sun Yat-sen University · Shenzhen Key Laboratory of Adversarial Artificial Intelligence · Chongqing University +1

  3. Hawkeye: Reading Illegible Text with Vision Language Models

    Oct 30, 2026Brian Tang, Kang G. ShinScene Text RecognitionVision-Language Models

    University of Michigan, Ann Arbor, MI 48105, USA

  4. When VLMs Trust Context: Evaluating Scene Text Recognition under Misleading Context

    Sep 28, 2026Yuxing Cheng, Yuan Wu, Yi ChangVLM EvaluationCounterfactual Evaluation of VLMs

    School of Artificial Intelligence, Jilin University · Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China · International Center of Future Science, Jilin University

  5. Back-Tracking from Clarity: Self-Learning to See Text from Afar

    Sep 26, 2026Duc-Tri Tran, Phi Le Nguyen, Minh HoaiScene Text RecognitionSelf-Supervised Learning

    Institute for AI Innovation & Societal Impact, Hanoi Univ. of Science & Technology · Australian Institute for Machine Learning, Adelaide University

  6. MEVL-STP: Multi-Encoder and Vision Language Model for Arbitrarily Shaped Scene Text Spotting

    Sep 23, 2026Aman Anand, Partha Pratim Roy, Shivakumara PalaiahnakoteScene Text Recognition

    Rajiv Gandhi Institute of Petroleum Technology, India · Indian Institute of Technology (ISM) Dhanbad, India · University of Salford, UK

  7. All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

    Sep 21, 2026Xingsong Ye, Yongkun Du, Jiaxin Zhang +6Scene Text RecognitionMixture-of-Experts Models

    Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI · WeChat Vision, Tencent Inc. +1

  8. SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text Spotting

    Sep 7, 2026Xudong Xie, Yuzhe Li, Jing Shi +3Scene Text RecognitionSupervised Fine-Tuning

    Huazhong University of Science and Technology, Wuhan, China · Adobe Research, San Jose, USA

  9. Can Scene Text Recognition Read Rare Compositions?

    Sep 1, 2026Genpei ZhangScene Text RecognitionOptical Character Recognition

    University of Wisconsin–Madison

  10. Confidence-Aware Ensemble and Long-Word Refinement for Artistic Text Recognition

    Aug 30, 2026Lucas A. Dias, Henrique A. Schulz, Rafaela de Miranda +3Ensemble LearningScene Text Recognition

    Pontifical Catholic University of Paraná, Curitiba, Brazil

  11. ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement

    Aug 28, 2026Jinlong Li, Jiaming Ding, Dingfu Lu +8VLM RobustnessEgocentric VQA

    OPPO US AI Center, USA · University of Wisconsin–Madison, USA · University of California San Diego, USA

  12. ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction

    Aug 27, 2026Bojun Zhang, Junhong Liang, Feifei Zhai +2Vision-Language ModelsVLM Evaluation

    State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Mohamed bin Zayed University of Artificial Intelligence +1

  13. Systematic Literature Review of Machine Learning Models and Applications for Text Recognition

    Aug 27, 2026Nuzhat Khan, Ab Al-Hadi Ab Rahman, Shahriyar Masud Rizvi +5Multilingual OCROptical Character Recognition

    Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, Malaysia · Department of Electrical and Electronic Engineering, American International University-Bangladesh, 408/1, Kuratoli 1229, Bangladesh · Department of Electrical Engineering, Balochistan University of Information Technology, Engineering and Management Sciences, Quetta 87300, Pakistan +1

  14. Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition

    Aug 11, 2026Zhibin Ma, Pengwen Dai, Yi Liu +3Scene Text RecognitionEquivariant Neural Networks

    Shenzhen Campus of Sun Yat-sen University, China · Shenzhen Key Laboratory of Adversarial Artificial Intelligence, China · Baidu Inc., China +1

  15. BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models

    Aug 4, 2026Sadab Shiper, Tawsif Tashwar Dipto, Mir Md Inzamam +1VLM EvaluationScene Text Recognition

    Islamic University of Technology, Bangladesh · BRAC University, Bangladesh

  16. One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting

    Jul 30, 2026Rui Tang, Wentao Yang, Peirong Zhang +4Visual TokenizationScene Text Recognition

    South China University of Technology · Guangzhou, China · HiThink Research +1

  17. Out-of-Length Scene Text Recognition: A Two-Axis Diagnosis and a Training-Free Fix

    Jul 25, 2026Zobeir Raisi, John ZelekScene Text RecognitionLength Generalization

    aElectrical Engineering Department, Chabahar Maritime University, Chabahar, Iran · bDepartment of Systems Design Engineering, University of Waterloo, Waterloo, N2L 3G1, ON, Canada

  18. 2D Rotary Position Embedding for Scene Text Recognition with Transformers

    Jul 15, 2026Zobeir RaisiRotary Positional EmbeddingsCross-Attention

    Electrical Engineering Department, Chabahar Maritime University, Chabahar, Iran.

  19. HAT Super-Resolution and a PARSeq+CLIP4STR Voting Ensemble for Extreme In-the-Wild License Plate Recognition

    Jul 9, 2026Karthik Sivarama Krishnan, Koushik Sivarama KrishnanScene Text RecognitionAutomatic License Plate Recognition

    Independent Researcher · Ancestry

  20. Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications

    Jun 23, 2026Shayon Dasgupta, Avijit Dasgupta, C. V. JawaharVLM EvaluationScene Text Recognition

    IIT BHU · India · CVIT, IIIT Hyderabad

  21. Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

    Jun 23, 2026Xingsong Ye, Yongkun Du, Jiaxin Zhang +5Synthetic Data AugmentationScene Text Recognition

    Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI, Fudan University · WeChat Vision, Tencent Inc. +1

  22. TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance

    Jun 5, 2026Duc Tri Tran, Trung Thanh Nguyen, Vijay John +2Scene Text RecognitionVideo Surveillance

    RIKEN, Japan · Hanoi University of Science and Technology, Vietnam · Nagoya University, Japan +2

  23. Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting

    May 18, 2026Antonio Colombo, Giovanni BianchiScene Text Recognition

    School of Information, Polytechnic University of Turin, Italy

  24. Masked Next-Scale Prediction for Self-supervised Scene Text Recognition

    May 14, 2026Zhuohao Chen, Zeng Li, Yifei Zhang +2Scene Text RecognitionSelf-Supervised Visual Representation Learning

    1Nankai University · Institute of Information Engineering, Chinese Academy of Sciences · Department of Automation and BNRist, Tsinghua University

  25. Reading in the Dark: Low-light Scene Text Recognition

    Apr 26, 2026Xuanshuo Fu, Lei Kang, Ernest Valveny +2Scene Text RecognitionLow-Light Image Enhancement

    Computer Vision Center, Barcelona, Spain

  26. JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding

    Mar 30, 2026Koki Maeda, Naoaki OkazakiVLM EvaluationScene Text Recognition

    Institute of Science Tokyo, Tokyo, Japan · Research and Development Center for Large Language Models, National Institute of Informatics, Tokyo, Japan

  27. SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia

    Mar 16, 2026Pengfei Yue, Xingran Zhao, Juntao Chen +6Multilingual VLM EvaluationDocument Parsing

    Xiamen University, China · Shopee, China · Tongji University, China

  28. Multi-Modal Character Localization and Extraction for Chinese Text Recognition

    Mar 14, 2026Qilong Li, Chongsheng ZhangScene Text RecognitionOptical Character Recognition

    School of Computer and Information Engineering and the Henan Provincial Key Laboratory of Big Data Analysis and Processing, Henan University, Kaifeng, P.R. China.

  29. An Effective Data Augmentation Method by Asking Questions about Scene Text Images

    Mar 3, 2026Xu Yao, Lei KangOptical Character RecognitionScene Text Recognition

    Computer Vision Center, Barcelona, Spain