AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

CoMER: Modeling Coverage for Transformer-Based Handwritten Mathematical Expression Recognition

Wenqi Zhao, Liangcai Gao

ECCV 2022 · Architectures and efficiency › Attention and transformers · approach: Attention head and block redesign · 71 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 scale augmentation to BTTR training (ablation)BTTR · CROHME 2014 testExpRate (%): 53.45 -> 55.17Improved
add self-coverage ARM to the transformer decoder (ablation)BTTR (baseline) · CROHME 2014 testExpRate (%): 55.17 -> 57.51 (+2.34)Improved
add cross-coverage ARM to the transformer decoder (ablation)BTTR (baseline) · CROHME 2014 testExpRate (%): 55.17 -> 58.11 (+2.94)Improved
combine self-coverage and cross-coverage (fusion) (ablation)CoMER (Self) · CROHME 2014 testExpRate (%): 57.51 -> 59.33Improved
add self-coverage to cross-coverage CoMER (fusion) (ablation)CoMER (Cross) · CROHME 2014 testExpRate (%): 58.11 -> 59.33Improved
replace vanilla transformer decoder with CoMER (ARM + fusion coverage)BTTR (baseline) · CROHME 2016 testExpRate (%): 56.58 -> 59.81Improved
replace vanilla transformer decoder with CoMER (ARM + fusion coverage)BTTR (baseline) · CROHME 2019 testExpRate (%): 59.55 -> 62.97Improved
replace vanilla transformer decoder with CoMER (ARM + fusion coverage)BTTR (baseline) · CROHME 2014 testExpRate (%): 55.17 -> 59.33Improved
use CoMER instead of the best RNN coverage model (Ding et al.)CoMER · CROHME 2014 testExpRate (%): 58.72 -> 59.33Improved
use CoMER instead of Ding et al.CoMER · CROHME 2019 testExpRate (%): 61.38 -> 62.97Improved
use CoMER instead of Ding et al. on <=3 errorsCoMER · CROHME 2014 testExpRate with <=3 errors (%): 78.60 -> 77.89Hurt
add coverage ARM (Fusion) for long expressions (ablation)BTTR (baseline) · CROHME 2014 test, sequences longer than 50accuracy by length: up to 5x BTTR (baseline)Improved

Later papers that compared with this method

2 later accepted papers report CoMER as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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