mlsanityData to 7 Oct 2026

Rosetta: Large scale system for text detection and recognition in images

arXiv 1910.05085 ↗First posted 11 Oct 2019cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

In this paper we present a deployed, scalable optical character recognition (OCR) system, which we call Rosetta, designed to process images uploaded daily at Facebook scale. Sharing of image content has become one of the primary ways to communicate information among internet users within social networks such as Facebook and Instagram, and the understanding of such media, including its textual information, is of paramount importance to facilitate search and recommendation applications. We present modeling techniques for efficient detection and recognition of text in images and describe Rosetta's system architecture. We perform extensive evaluation of presented technologies, explain useful practical approaches to build an OCR system at scale, and provide insightful intuitions as to why and how certain components work based on the lessons learnt during the development and deployment of the system.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 21; 2023: 18; 2024: 6; 2025: 5; 2026: 3.

69 papers.

Sort:

By area:

  1. 2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 170
  2. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 148
  3. 2022PromptCap: Prompt-Guided Task-Aware Image Captioningcited by 104
  4. 2022SVTR: Scene Text Recognition with a Single Visual Modelcited by 86
  5. 2021Vision Transformer for Fast and Efficient Scene Text Recognitioncited by 81
  6. 2021Human-Adversarial Visual Question Answeringcited by 57
  7. 2023Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizercited by 53
  8. 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Modelscited by 52
  9. 2021MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understandingcited by 40
  10. 2022Multi-Granularity Prediction for Scene Text Recognitioncited by 36
  11. 2023CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Modelcited by 30
  12. 2021MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioningcited by 27
38 more
  1. 2022PreSTU: Pre-Training for Scene-Text Understandingcited by 27
  2. 2023Towards Unified Scene Text Spotting based on Sequence Generationcited by 27
  3. 2021Towards Accurate Text-based Image Captioning with Content Diversity Explorationcited by 25
  4. 2022On the Cross-dataset Generalization in License Plate Recognitioncited by 22
  5. 2023OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamesecited by 20
  6. 2023Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literaturecited by 20
  7. 2021Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmarkcited by 17
  8. 2021Localize, Group, and Select: Boosting Text-VQA by Scene Text Modelingcited by 14
  9. 2022Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognitioncited by 14
  10. 2023Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMscited by 14
  11. 2022Towards Open-Set Text Recognition via Label-to-Prototype Learningcited by 12
  12. 2022Weakly-supervised Fingerspelling Recognition in British Sign Language Videoscited by 10
  13. 2023Leveraging Model Fusion for Improved License Plate Recognitioncited by 10
  14. 2023What Large Language Models Bring to Text-rich VQA?cited by 10
  15. 2024ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spottingcited by 10
  16. 2022Open-set Text Recognition via Character-Context Decouplingcited by 8
  17. 2024Lumos : Empowering Multimodal LLMs with Scene Text Recognitioncited by 8
  18. 2023Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognitioncited by 7
  19. 2023Separate and Locate: Rethink the Text in Text-based Visual Question Answeringcited by 7
  20. 2023DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Modelscited by 7
  21. 2023An Empirical Study of Scaling Law for OCRcited by 7
  22. 2024InstructOCR: Instruction Boosting Scene Text Spottingcited by 7
  23. 2026Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluationcited by 7
  24. 2022TRIE++: Towards End-to-End Information Extraction from Visually Rich Documentscited by 6
  25. 2023Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQAcited by 6
  26. 2021Revisiting Classification Perspective on Scene Text Recognitioncited by 5
  27. 2021Digital Peter: Dataset, Competition and Handwriting Recognition Methodscited by 5
  28. 2021Data Augmentation for Scene Text Recognitioncited by 5
  29. 2022Look, Read and Ask: Learning to Ask Questions by Reading Text in Imagescited by 5
  30. 2024SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractorcited by 5
  31. 2021STRIDE : Scene Text Recognition In-Devicecited by 4
  32. 2022MUST-VQA: MUltilingual Scene-text VQAcited by 4
  33. 2023Multiple-Question Multiple-Answer Text-VQAcited by 4
  34. 2023DEVICE: Depth and Visual Concepts Aware Transformer for OCR-based Image Captioningcited by 3
  35. 2024Decoder Pre-Training with only Text for Scene Text Recognitioncited by 3
  36. 2021Event and Activity Recognition in Video Surveillance for Cyber-Physical Systemscited by 2
  37. 2022Image-based Automatic Dial Meter Reading in Unconstrained Scenarioscited by 2
  38. 20223D Rendering Framework for Data Augmentation in Optical Character Recognitioncited by 2

50 most cited of 69 All 69 (JSON)