Spatial Context-based Self-Supervised Learning for Handwritten Text Recognition
Not on the map. Why?
Abstract (arXiv)
Handwritten Text Recognition (HTR) is a relevant problem in computer vision, and implies unique challenges owing to its inherent variability and the rich contextualization required for its interpretation. Despite the success of Self-Supervised Learning (SSL) in computer vision, its application to HTR has been rather scattered, leaving key SSL methodologies unexplored. This work focuses on one of them, namely Spatial Context-based SSL. We investigate how this family of approaches can be adapted and optimized for HTR and propose new workflows that leverage the unique features of handwritten text. Our experiments demonstrate that the methods considered lead to advancements in the state-of-the-art of SSL for HTR in a number of benchmark cases.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 51 of its 85 references that are in the map. First posted on arXiv 17 Apr 2024.
Builds on
51 of 85 references.
References · 51
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
- 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
38 more
- 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
- 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
- 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
- 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
- 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
- 2020Self-supervised Learning: Generative or Contrastivecited by 694
- 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
- 2020A Survey on Contrastive Self-supervised Learningcited by 554
- 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
- 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 279
- 2023A Cookbook of Self-Supervised Learningcited by 250
- 2019What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysiscited by 191
- 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
- 2017Focusing Attention: Towards Accurate Text Recognition in Natural Imagescited by 110
- 2018Self-Supervised GANs via Auxiliary Rotation Losscited by 94
- 2019AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Datacited by 77
- 2020Sequence-to-Sequence Contrastive Learning for Text Recognitioncited by 70
- 2022Audio Self-supervised Learning: A Surveycited by 65
- 2022DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognitioncited by 62
- 2019Evaluating Sequence-to-Sequence Models for Handwritten Text Recognitioncited by 58
- 2020End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Networkcited by 50
- 2021Rethinking Text Line Recognition Modelscited by 45
- 2022Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognitioncited by 45
- 2023DTrOCR: Decoder-only Transformer for Optical Character Recognitioncited by 40
- 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
- 2022MaskOCR: Text Recognition with Masked Encoder-Decoder Pretrainingcited by 34
- 2018Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspectioncited by 27
- 2022SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalizationcited by 21
- 2020Boosting offline handwritten text recognition in historical documents with few labeled linescited by 19
- 2021Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixescited by 18
- 2020Attention-based Fully Gated CNN-BGRU for Russian Handwritten Textcited by 17
- 2022Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancementcited by 16
- 2022AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networkscited by 12
- 2017Character-Based Handwritten Text Transcription with Attention Networkscited by 11
- 2023A Transformer-based Approach for Arabic Offline Handwritten Text Recognitioncited by 9
- 2023End-to-End Page-Level Assessment of Handwritten Text Recognitioncited by 8
- 2019Image Enhanced Rotation Prediction for Self-Supervised Learningcited by 7
- 2022Lexicon and Attention based Handwritten Text Recognition Systemcited by 5
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.