Image To Latex with DenseNet Encoder and Joint Attention | Zendy

Jian Wang | Zendy; Yunchuan Sun | Zendy; Shenling Wang | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Image To Latex with DenseNet Encoder and Joint Attention

Author(s) -

Jian Wang,

Yunchuan Sun,

Shenling Wang

Publication year - 2019

Publication title -

procedia computer science

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.334

H-Index - 76

ISSN - 1877-0509

DOI - 10.1016/j.procs.2019.01.246

Subject(s) - computer science , closed captioning , encoder , joint (building) , sequence (biology) , feature (linguistics) , field (mathematics) , artificial intelligence , image (mathematics) , baseline (sea) , convolutional neural network , pattern recognition (psychology) , architectural engineering , linguistics , philosophy , oceanography , mathematics , biology , pure mathematics , engineering , genetics , geology , operating system

Mathematical formula structural analysis usually converts mathematical formulas in images into Latex codes. It has been named as Image2Latex by OpenAi. At present, many researchers use the model in the field of image captioning for image2latex and have achieved good results. In this paper, we propose some improvements to the baseline model which is a sequence-to-sequence model used in image caption. We improve the encoder by employing densely connected convolutional network (DenseNet) because it can strengthen feature extraction and facilitate gradient propagation. We propose to use a more effective joint attention mechanism which include both spatial attention and channel-wise attention to solve this problem. We conducted experiments on the dataset im2latex-100k. Experimental results showed that our model improved the performance of formula analysis.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research