OpenCodePapers

handwritten-mathmatical-expression-recognition-on-crohme-2016

Optical Character Recognition (OCR)Handwritten Mathematical Expression Recognition
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeExpRateModelNameReleaseDate
Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition✓ Link77.94Uni-MuMER2025-05-29
PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer✓ Link60.94PosFormer2024-07-10
TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition✓ Link60.26TAMER2024-08-16
NAMER: Non-Autoregressive Modeling for Handwritten Mathematical Expression Recognition60.24NAMER2024-07-16
ICAL: Implicit Character-Aided Learning for Enhanced Handwritten Mathematical Expression Recognition✓ Link58.79ICAL2024-05-15
CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition✓ Link56.98CoMER2022-07-10
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition✓ Link56.15CAN-ABM2022-07-23
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition✓ Link56.06CAN-DWAP2022-07-23
TDv2: A Novel Tree-Structured Decoder for Offline Mathematical Expression Recognition55.18TDv22022-06-28
Syntax-Aware Network for Handwritten Mathematical Expression Recognition✓ Link53.6SAN2022-03-03
Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning✓ Link52.92ABM2021-12-07
Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer✓ Link52.31BTTR2021-05-06
Multi-Scale Dense Networks for Resource Efficient Image Classification✓ Link50.1DenseWAP-MSA2017-03-29
A Tree-Structured Decoder for Image-to-Markup Generation✓ Link48.5TD
Multi-Scale Dense Networks for Resource Efficient Image Classification✓ Link47.5DenseWAP2017-03-29
Watch, attend and parse: An end-to-end neural network based approach to handwritten mathematical expression recognition✓ Link44.55WAP2017-07-01
Check out how to contribute new results. Then edit this file on GitLab or GitHub.