AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition

Bohan Li, Ye Yuan, Dingkang Liang, Xiao Liu, Zhilong Ji, Jinfeng Bai, Wenyu Liu, Xiang Bai

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 70 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add positional encoding (ablation)DWAP · CROHME 2014ExpRate: 51.48 -> 51.88Improved
add joint optimization with symbol counting (ablation)DWAP + positional encoding · CROHME 2014ExpRate: 51.88 -> 55.23Improved
add counting vector to the decoder (ablation)DWAP + positional encoding + joint optimization · CROHME 2014ExpRate: 55.23 -> 57.00Improved
add counting vector to the decoder (ablation)DWAP + positional encoding + joint optimization · CROHME 2019ExpRate: 53.13 -> 54.88Improved
use both 3x3 and 5x5 kernels instead of 3x3 in counting module (ablation)CAN-DWAP · CROHME 2014ExpRate: 54.92 -> 57.00Improved
use both 3x3 and 5x5 kernels instead of 5x5 in counting module (ablation)CAN-DWAP · CROHME 2014ExpRate: 55.53 -> 57.00Improved
feed ground-truth counting vector to the decoder (ablation)CAN-DWAP · CROHME 2014ExpRate: 57.00 -> 62.44Improved
add random disturbance to counting vector (more inaccurate) (ablation)CAN-DWAP with counting GT · CROHME 2014ExpRate: 62.44 -> 60.10 -> 58.28Hurt
train counting jointly with HMER instead of counting alone (ablation)CAN counting module · CROHME 2014MAE_Ave: 0.048 -> 0.033Improved
add counting module (CAN) to DWAPDWAP · CROHME 2014 (no augmentation)ExpRate: 51.48 -> 57.00Improved
add counting module (CAN) to DWAP with data augmentationDWAP · CROHME 2014 (with augmentation)ExpRate: 57.97 -> 65.58Improved
add counting module (CAN) to ABMABM · HME100KExpRate: 65.93 -> 68.09Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy