AI Paper Atlas

Research map / Detection and segmentation / CNN features

SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting

Mingxin Huang, Dezhi Peng, Hongliang Li, Zhenghao Peng, Chongyu Liu, Dahua Lin, Yuliang Liu, Xiang Bai, Lianwen Jin

IJCV 2025 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 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 Box Selection Schedule (ablation)Baseline+TRS · Total-TextE2E H-mean: 63.3 -> 67.9Improved
add Box Selection Schedule (ablation)Baseline+TRS · ICDAR 2015 GenericH-mean: 61.4 -> 65.4Improved
add Recognition Alignment (ablation)Baseline+TRS · Total-TextE2E H-mean: 63.3 -> 65.1Improved
add Recognition Alignment (ablation)Baseline+TRS · ICDAR 2015 GenericH-mean: 61.4 -> 64.7Improved
add RA on top of TRS+BSS (ablation)SwinTextSpotter v2 · Total-TextE2E H-mean: 67.9 -> 71.3Improved
add Recognition Conversion (ablation)SwinTextSpotter v2 · Total-TextE2E H-mean: 68.1 -> 71.3Improved
add TLSAM (ablation)SwinTextSpotter v2 · Total-TextE2E H-mean: 70.6 -> 71.3Improved
add TLSAM (ablation)SwinTextSpotter v2 · ICDAR 2015 StrongH-mean: 80.5 -> 81.8Improved
add both RC and TLSAM (ablation)SwinTextSpotter v2 · Total-TextE2E H-mean: 66.4 -> 71.3Improved
add local-level attention alignment (ablation)SwinTextSpotter v2 · Total-Text E2E NoneH-mean: 67.9 -> 69.4Improved
add global-level attention alignment (ablation)SwinTextSpotter v2 · Total-Text E2E NoneH-mean: 67.9 -> 68.7Improved
increase refinement stages from two to three (ablation)SwinTextSpotter v2 · Total-Text E2EH-mean: 65.9 -> 71.3Improved

Later papers that compared with this method

1 later accepted paper reports SwinTextSpotter v2 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 0 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