# Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network

arXiv: https://arxiv.org/abs/2012.04961 · HTML: https://mlsanity.com/paper/2012.04961/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 23 of 23)

- [DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition](https://mlsanity.com/paper/2203.12273/) (2022)
- [HTR-VT: Handwritten Text Recognition with Vision Transformer](https://mlsanity.com/paper/2409.08573/) (2024)
- [SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition](https://mlsanity.com/paper/2102.08742/) (2021)
- [The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition](https://mlsanity.com/paper/2208.07682/) (2022)
- [Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions](https://mlsanity.com/paper/2208.08109/) (2022)
- [How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning](https://mlsanity.com/paper/2305.02593/) (2023)
- [Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition](https://mlsanity.com/paper/2301.10593/) (2023)
- [DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents](https://mlsanity.com/paper/2407.09103/) (2024)
- [Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition](https://mlsanity.com/paper/2407.13559/) (2024)
- [Easter2.0: Improving convolutional models for handwritten text recognition](https://mlsanity.com/paper/2205.14879/) (2022)
- [Searching a High-Performance Feature Extractor for Text Recognition Network](https://mlsanity.com/paper/2209.13139/) (2022)
- [Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition](https://mlsanity.com/paper/2504.03349/) (2025)
- [StackMix and Blot Augmentations for Handwritten Text Recognition](https://mlsanity.com/paper/2108.11667/) (2021)
- [CALText: Contextual Attention Localization for Offline Handwritten Text](https://mlsanity.com/paper/2111.03952/) (2021)
- [Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?](https://mlsanity.com/paper/2508.09936/) (2025)
- [Handwritten text generation and strikethrough characters augmentation](https://mlsanity.com/paper/2112.07395/) (2021)
- [Combining OCR Models for Reading Early Modern Printed Books](https://mlsanity.com/paper/2305.07131/) (2023)
- [HTR-ConvText: Leveraging Convolution and Textual Information for Handwritten Text Recognition](https://mlsanity.com/paper/2512.05021/) (2025)
- [Understanding Cross-Language Transfer Improvements in Low-Resource HTR: The Role of Sequence Modeling](https://mlsanity.com/paper/2605.05900/) (2026)
- [Towards Robust Handwritten Text Recognition with On-the-fly User Participation](https://mlsanity.com/paper/2212.08834/) (2022)
- [CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition](https://mlsanity.com/paper/2303.09347/) (2023)
- [Boosting CNN-based Handwriting Recognition Systems with Learnable Relaxation Labeling](https://mlsanity.com/paper/2409.05699/) (2024)
- [N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition](https://mlsanity.com/paper/2603.03930/) (2026)

## Abstract (arXiv)

Unconstrained handwritten text recognition is a major step in most document analysis tasks. This is generally processed by deep recurrent neural networks and more specifically with the use of Long Short-Term Memory cells. The main drawbacks of these components are the large number of parameters involved and their sequential execution during training and prediction. One alternative solution to using LSTM cells is to compensate the long time memory loss with an heavy use of convolutional layers whose operations can be executed in parallel and which imply fewer parameters. In this paper we present a Gated Fully Convolutional Network architecture that is a recurrence-free alternative to the well-known CNN+LSTM architectures. Our model is trained with the CTC loss and shows competitive results on both the RIMES and IAM datasets. We release all code to enable reproduction of our experiments: https://github.com/FactoDeepLearning/LinePytorchOCR.