mlsanityData to 7 Oct 2026

SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition

arXiv 2102.08742 ↗First posted 17 Feb 2021cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Unconstrained handwriting recognition is an essential task in document analysis. It is usually carried out in two steps. First, the document is segmented into text lines. Second, an Optical Character Recognition model is applied on these line images. We propose the Simple Predict & Align Network: an end-to-end recurrence-free Fully Convolutional Network performing OCR at paragraph level without any prior segmentation stage. The framework is as simple as the one used for the recognition of isolated lines and we achieve competitive results on three popular datasets: RIMES, IAM and READ 2016. The proposed model does not require any dataset adaptation, it can be trained from scratch, without segmentation labels, and it does not require line breaks in the transcription labels. Our code and trained model weights are available at https://github.com/FactoDeepLearning/SPAN.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 13 of its 24 references that are in the map. First posted on arXiv 17 Feb 2021.

Builds on

13 of 24 references.

References · 13

  1. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  2. 2019Evaluating Sequence-to-Sequence Models for Handwritten Text Recognitioncited by 58
  3. 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldcited by 53
  4. 2020End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Networkcited by 50
  5. 2016Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognitioncited by 46
  6. 2016Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attentioncited by 45
  7. 2018dhSegment: A generic deep-learning approach for document segmentationcited by 32
  8. 2018Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networkscited by 31
  9. 2018A Two-Stage Method for Text Line Detection in Historical Documentscited by 26
  10. 2020Recurrence-free unconstrained handwritten text recognition using gated fully convolutional networkcited by 23
  11. 2019A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pagescited by 16
  12. 2019A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognitioncited by 9
1 more
  1. 2020Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?cited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 4; 2025: 5; 2026: 3.

19 papers.

Sort:

By area:

  1. 2022DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognitioncited by 62
  2. 2024HTR-VT: Handwritten Text Recognition with Vision Transformercited by 24
  3. 2025Handwritten Text Recognition: A Surveycited by 12
  4. 2023Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognitioncited by 9
  5. 2024DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documentscited by 9
  6. 2023End-to-End Page-Level Assessment of Handwritten Text Recognitioncited by 8
  7. 2023MSdocTr-Lite: A Lite Transformer for Full Page Multi-script Handwriting Recognitioncited by 7
  8. 2025DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learningcited by 3
  9. 2025Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognitioncited by 3
  10. 2025MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuningcited by 2
  11. 2023Combining OCR Models for Reading Early Modern Printed Bookscited by 1
  12. 2025RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognitioncited by 1
7 more
  1. 2026Few-shot Writer Adaptation via Multimodal In-Context Learningcited by 1
  2. 2026A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCRcited by 1
  3. 2022Proceedings of the 4th International Workshop on Reading Music Systemscited by 0
  4. 2023Proceedings of the 5th International Workshop on Reading Music Systemscited by 0
  5. 2024Understanding attention-based encoder-decoder networks: a case study with chess scoresheet recognitioncited by 0
  6. 2024Block-level Text Spotting with LLMscited by 0
  7. 2026ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Expertscited by 0