A vision transformer encoder with a transformer decoder beats small CNN-LSTM and ResNet-LSTM baselines on image-to-LaTeX conversion in the authors' reported experiments.
Guillaume Genthial and Romain Sauvestre
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Automated LaTeX Code Generation from Handwritten Math Expressions Using Vision Transformer
A vision transformer encoder with a transformer decoder beats small CNN-LSTM and ResNet-LSTM baselines on image-to-LaTeX conversion in the authors' reported experiments.