# ConvMath: A Convolutional Sequence Network for Mathematical Expression Recognition

arXiv: https://arxiv.org/abs/2012.12619 · HTML: https://mlsanity.com/paper/2012.12619/

## Key facts

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

## Built on by (most cited first, 9 of 9)

- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion](https://mlsanity.com/paper/2503.11576/) (2025)
- [Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer](https://mlsanity.com/paper/2105.02412/) (2021)
- [Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning](https://mlsanity.com/paper/2112.03603/) (2021)
- [LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement](https://mlsanity.com/paper/2409.14201/) (2024)
- [MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition](https://mlsanity.com/paper/2404.13667/) (2024)
- [Offline Handwritten Mathematical Recognition using Adversarial Learning and Transformers](https://mlsanity.com/paper/2208.09662/) (2022)
- [Dual Branch Network Towards Accurate Printed Mathematical Expression Recognition](https://mlsanity.com/paper/2312.09030/) (2023)
- [A Hybrid Vision Transformer Approach for Mathematical Expression Recognition](https://mlsanity.com/paper/2603.07929/) (2026)

## Abstract (arXiv)

Despite the recent advances in optical character recognition (OCR), mathematical expressions still face a great challenge to recognize due to their two-dimensional graphical layout. In this paper, we propose a convolutional sequence modeling network, ConvMath, which converts the mathematical expression description in an image into a LaTeX sequence in an end-to-end way. The network combines an image encoder for feature extraction and a convolutional decoder for sequence generation. Compared with other Long Short Term Memory(LSTM) based encoder-decoder models, ConvMath is entirely based on convolution, thus it is easy to perform parallel computation. Besides, the network adopts multi-layer attention mechanism in the decoder, which allows the model to align output symbols with source feature vectors automatically, and alleviates the problem of lacking coverage while training the model. The performance of ConvMath is evaluated on an open dataset named IM2LATEX-100K, including 103556 samples. The experimental results demonstrate that the proposed network achieves state-of-the-art accuracy and much better efficiency than previous methods.