# Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition

arXiv: https://arxiv.org/abs/2504.03349 · HTML: https://mlsanity.com/paper/2504.03349/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training](https://mlsanity.com/paper/2001.04063/) (2020)
- [DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition](https://mlsanity.com/paper/2203.12273/) (2022)
- [Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition](https://mlsanity.com/paper/1903.07377/) (2019)
- [OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold](https://mlsanity.com/paper/2006.07491/) (2020)
- [End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network](https://mlsanity.com/paper/2012.03868/) (2020)
- [Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition](https://mlsanity.com/paper/1604.08352/) (2016)
- [Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention](https://mlsanity.com/paper/1604.03286/) (2016)
- [Rethinking Text Line Recognition Models](https://mlsanity.com/paper/2104.07787/) (2021)
- [Full Page Handwriting Recognition via Image to Sequence Extraction](https://mlsanity.com/paper/2103.06450/) (2021)
- [Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network](https://mlsanity.com/paper/2012.04961/) (2020)
- [SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition](https://mlsanity.com/paper/2102.08742/) (2021)
- [Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documents](https://mlsanity.com/paper/2112.04189/) (2021)
- [A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages](https://mlsanity.com/paper/1912.10016/) (2019)
- [Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition](https://mlsanity.com/paper/2301.10593/) (2023)
- [Key-value information extraction from full handwritten pages](https://mlsanity.com/paper/2304.13530/) (2023)
- [DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents](https://mlsanity.com/paper/2407.09103/) (2024)
- [The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censuses](https://mlsanity.com/paper/2404.18706/) (2024)
- [End-to-end information extraction in handwritten documents: Understanding Paris marriage records from 1880 to 1940](https://mlsanity.com/paper/2404.19329/) (2024)
- [Whole page recognition of historical handwriting](https://mlsanity.com/paper/2009.10634/) (2020)
- [Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel](https://mlsanity.com/paper/2107.01547/) (2021)

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

- [N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition](https://mlsanity.com/paper/2603.03930/) (2026)
- [Performance Gap Analysis between Latin and Arabic Scripts HTR](https://mlsanity.com/paper/2606.18884/) (2026)
- [ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Experts](https://mlsanity.com/paper/2609.12705/) (2026)

## Abstract (arXiv)

Recent advances in text recognition led to a paradigm shift for page-level recognition, from multi-step segmentation-based approaches to end-to-end attention-based ones. However, the na"ive character-level autoregressive decoding process results in long prediction times: it requires several seconds to process a single page image on a modern GPU. We propose the Meta Document Attention Network (Meta-DAN) as a novel decoding strategy to reduce the prediction time while enabling a better context modeling. It relies on two main components: windowed queries, to process several transformer queries altogether, enlarging the context modeling with near future; and multi-token predictions, whose goal is to predict several tokens per query instead of only the next one. We evaluate the proposed approach on 10 full-page handwritten datasets and demonstrate state-of-the-art results on average in terms of character error rate. Source code and weights of trained models are available at https://github.com/FactoDeepLearning/metadan.