SemiHMER combines dual-branch pseudo-supervision, weak-to-strong augmentation, and a dynamic counting module to improve handwritten math formula recognition on CROHME benchmarks.
: Primitive con- trastive learning for handwritten mathematical expressio n recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SemiHMER: Semi-supervised Handwritten Mathematical Expression Recognition using pseudo-labels
SemiHMER combines dual-branch pseudo-supervision, weak-to-strong augmentation, and a dynamic counting module to improve handwritten math formula recognition on CROHME benchmarks.