English

Image-to-Markup Generation with Coarse-to-Fine Attention

Computer Vision and Pattern Recognition 2017-06-15 v2 Computation and Language Machine Learning Neural and Evolutionary Computing

Abstract

We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism. Our method is evaluated in the context of image-to-LaTeX generation, and we introduce a new dataset of real-world rendered mathematical expressions paired with LaTeX markup. We show that unlike neural OCR techniques using CTC-based models, attention-based approaches can tackle this non-standard OCR task. Our approach outperforms classical mathematical OCR systems by a large margin on in-domain rendered data, and, with pretraining, also performs well on out-of-domain handwritten data. To reduce the inference complexity associated with the attention-based approaches, we introduce a new coarse-to-fine attention layer that selects a support region before applying attention.

Keywords

Cite

@article{arxiv.1609.04938,
  title  = {Image-to-Markup Generation with Coarse-to-Fine Attention},
  author = {Yuntian Deng and Anssi Kanervisto and Jeffrey Ling and Alexander M. Rush},
  journal= {arXiv preprint arXiv:1609.04938},
  year   = {2017}
}

Comments

Accepted by ICML 2017

R2 v1 2026-06-22T15:51:36.384Z