mlsanityData to 14 Oct 2026

Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis

arXiv 2310.17674 ↗First posted 25 Oct 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We propose Hierarchical Text Spotter (HTS), a novel method for the joint task of word-level text spotting and geometric layout analysis. HTS can recognize text in an image and identify its 4-level hierarchical structure: characters, words, lines, and paragraphs. The proposed HTS is characterized by two novel components: (1) a Unified-Detector-Polygon (UDP) that produces Bezier Curve polygons of text lines and an affinity matrix for paragraph grouping between detected lines; (2) a Line-to-Character-to-Word (L2C2W) recognizer that splits lines into characters and further merges them back into words. HTS achieves state-of-the-art results on multiple word-level text spotting benchmark datasets as well as geometric layout analysis tasks.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 59 of its 67 references that are in the map. First posted on arXiv 25 Oct 2023.

Builds on

59 of 67 references.

References · 59

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2016Layer Normalizationcited by 5,669
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2019Towards VQA Models That Can Readcited by 1,718
  10. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  11. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 485
  12. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
38 more
  1. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  2. 2019PubLayNet: largest dataset ever for document layout analysiscited by 351
  3. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 349
  4. 2019Scene Text Visual Question Answeringcited by 331
  5. 2019Character Region Awareness for Text Detectioncited by 278
  6. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  7. 2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 171
  8. 2017Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognitioncited by 162
  9. 2022Scene Text Recognition with Permuted Autoregressive Sequence Modelscited by 149
  10. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 148
  11. 2018TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapescited by 114
  12. 2018Scene Text Detection and Recognition: The Deep Learning Eracited by 114
  13. 2020Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spottingcited by 114
  14. 2018FOTS: Fast Oriented Text Spotting with a Unified Networkcited by 109
  15. 2022Towards End-to-End Unified Scene Text Detection and Layout Analysiscited by 97
  16. 2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
  17. 2017Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networkcited by 92
  18. 2021StructuralLM: Structural Pre-training for Form Understandingcited by 91
  19. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  20. 2017Detecting Curve Text in the Wild: New Dataset and New Solutioncited by 83
  21. 2017Detecting Oriented Text in Natural Images by Linking Segmentscited by 80
  22. 2022Text Spotting Transformerscited by 70
  23. 2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
  24. 2022FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extractioncited by 64
  25. 2019Convolutional Character Networkscited by 61
  26. 2018Scene Text Recognition from Two-Dimensional Perspectivecited by 57
  27. 2019Towards Unconstrained End-to-End Text Spottingcited by 57
  28. 2020MANGO: A Mask Attention Guided One-Stage Scene Text Spottercited by 51
  29. 2022DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformercited by 50
  30. 2021Open Images V5 Text Annotation and Yet Another Mask Text Spottercited by 46
  31. 2021SPTS: Single-Point Text Spottingcited by 45
  32. 2020UnrealText: Synthesizing Realistic Scene Text Images from the Unreal Worldcited by 43
  33. 2021SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Modelscited by 43
  34. 2020Character Region Attention For Text Spottingcited by 42
  35. 2022Towards Weakly-Supervised Text Spotting using a Multi-Task Transformercited by 41
  36. 2022Multi-Granularity Prediction for Scene Text Recognitioncited by 36
  37. 2021Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Featurescited by 34
  38. 2022GLASS: Global to Local Attention for Scene-Text Spottingcited by 34

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 1.

8 papers.

  1. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  2. 2025OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Modelscited by 23
  3. 2024Bridging the Gap Between End-to-End and Two-Step Text Spottingcited by 9
  4. 2024TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Modelcited by 5
  5. 2025PILOT: A Promptable Interleaved Layout-aware OCR Transformercited by 2
  6. 2024Block-level Text Spotting with LLMscited by 0
  7. 2025LIGHT: Multi-Modal Text Linking on Historical Mapscited by 0
  8. 2026TableSeq: Unified Generation of Structure, Content, and Layoutcited by 0