# Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory

arXiv: https://arxiv.org/abs/1911.01577 · HTML: https://mlsanity.com/paper/1911.01577/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [Memory and attention in deep learning](https://mlsanity.com/paper/2107.01390/) (2021)
- [HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System](https://mlsanity.com/paper/2206.02628/) (2022)
- [Out-of-Length Scene Text Recognition: A Two-Axis Diagnosis and a Training-Free Fix](https://mlsanity.com/paper/2607.23194/) (2026)

## Abstract (arXiv)

Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. This poses a major challenge to goal of completely solving Optical Character Recognition (OCR) problem. Inspired by recently proposed memory-augmented neural networks (MANNs) for long-term sequential modeling, we present a new architecture dubbed Convolutional Multi-way Associative Memory (CMAM) to tackle the limitation of current CRNNs. By leveraging recent memory accessing mechanisms in MANNs, our architecture demonstrates superior performance against other CRNN counterparts in three real-world long text OCR datasets.