AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer

Tongkun Guan, Chengyu Lin, Wei Shen, Xiaokang Yang

ECCV 2024 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and circuits · 29 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 Position Forest auxiliary position recognition task (ablation)CoMER baseline · CROHME 2014ExpRate: 59.33 -> 62.13Improved
add Position Forest auxiliary position recognition task (ablation)CoMER baseline · CROHME 2019ExpRate: 62.97 -> 63.80Improved
add Implicit Attention Correction on top of Position Forest (ablation)PosFormer · CROHME 2014ExpRate: 62.13 -> 62.64Improved
add Implicit Attention Correction on top of Position Forest (ablation)PosFormer · CROHME 2016ExpRate: 61.03 -> 61.20Improved
add Position Forest to RNN-based DWAP (ablation)DWAP · CROHME 2014ExpRate: 50.10 -> 57.10Improved
add Position Forest to ABM (ablation)ABM · CROHME 2019ExpRate: 53.96 -> 54.30Improved
add Position Forest to CAN (ablation)CAN · CROHME 2019ExpRate: 52.96 -> 57.13Improved
use Position Forest versus RobustScanner position enhancement on DWAP (ablation)DWAP · Average over CROHME 14/16/19ExpRate: 53.18 -> 56.87Improved
use Position Forest versus the SAN tree decoder as auxiliary on DWAP (ablation)DWAP · CROHME 2014ExpRate: 50.41 -> 57.10Improved
PosFormer versus CoMER as nesting depth grows (N1, N2, N3)PosFormer · MNE test setExpRate: +0.86 (N1); +1.65 (N2); +10.04 (N3)Improved
Position Forest is used only in training and removed at inferencePosFormer · Inference speed vs CoMERFPS: 6.30 -> 6.28No clear effect

Later papers that compared with this method

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

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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