AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition

Xudong Xie, Ling Fu, Zhifei Zhang, Zhaowen Wang, Xiang Bai

ECCV 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 92 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 corner-map branch with corner-query cross-attention (ablation)SATRN baseline · WordArtword accuracy: 67.0 -> 69.1Improved
feed image instead of corner map to the extra branch (ablation)SATRN baseline with cross-attention · WordArtword accuracy: 67.0 -> 66.0Hurt
replace cross-attention with extra self-attention (no corner input) (ablation)SATRN baseline · WordArtword accuracy: 67.0 -> 67.6No clear effect
use Harris instead of Shi-Tomasi corner detector (ablation)Corner-guided encoder · WordArtword accuracy: 69.1 -> 68.4Hurt
use SuperPoint instead of Shi-Tomasi corner detector (ablation)Corner-guided encoder · WordArtword accuracy: 69.1 -> 69.0No clear effect
use corner as key/value instead of query (ablation)Corner-guided encoder · WordArtword accuracy: 69.1 -> 66.9Hurt
fuse corner and image by concatenation instead of corner-query attention (ablation)SATRN baseline · WordArtword accuracy: 69.1 -> 67.0Hurt
fuse corner and image by addition instead of corner-query attention (ablation)SATRN baseline · WordArtword accuracy: 69.1 -> 66.6Hurt
fuse corner and image by multiplication instead of corner-query attention (ablation)SATRN baseline · WordArtword accuracy: 69.1 -> 67.4Hurt
add character contrastive loss (lambda 0.1, tau 0.1, d 2048) (ablation)SATRN baseline · WordArtword accuracy: 67.0 -> 68.6Improved
lower temperature tau to 0.05 in CC loss (ablation)CC loss (lambda 0.1, d 512) · WordArtword accuracy: 68.1 -> 66.5Hurt
raise CC loss weight lambda to 1 (ablation)CC loss (tau 0.1, d 2048) · WordArtword accuracy: 68.6 -> 66.6Hurt

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