AI Paper Atlas

Research map / Detection and segmentation / CNN features

Single Shot Text Detector With Regional Attention

Pan He, Weilin Huang, Tong He, Qile Zhu, Yu Qiao, Xiaolin Li

ICCV 2017 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 344 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 text attention module (TAM) (ablation)Baseline SSD-based text detector · ICDAR 2013 (new standard)F-measure: 0.82 -> 0.85Improved
add text attention module (TAM) (ablation)Baseline SSD-based text detector · ICDAR 2013 (new standard)recall: 0.78 -> 0.83Improved
add hierarchical inception module (HIM) (ablation)Baseline SSD-based text detector · ICDAR 2013 (new standard)F-measure: 0.82 -> 0.84Improved
add hierarchical inception module (HIM) (ablation)Baseline SSD-based text detector · ICDAR 2013 (new standard)recall: 0.78 -> 0.82Improved
add both TAM and HIM (ablation)Baseline SSD-based text detector · ICDAR 2013 (new standard)F-measure: 0.82 -> 0.87Improved
add both TAM and HIM (ablation)Baseline SSD-based text detector · ICDAR 2013 (new standard)precision: 0.87 -> 0.88Improved
add SSD-based modifications for text word prediction (baseline model vs plain SSD) (ablation)SSD · ICDAR 2013 (new standard)F-measure: 0.68 -> 0.82Improved
add TAM on top of HIM (full model vs HIM only) (ablation)Baseline SSD-based text detector + HIM · ICDAR 2013 (new standard)F-measure: 0.84 -> 0.87Improved
full model vs CTPN under DetEvalProposed detector · ICDAR 2013 (DetEval)F-measure: 0.88 -> 0.88No clear effect
full model vs CTPN on multi-orientation textProposed detector · ICDAR 2015F-measure: 0.61 -> 0.77Improved
full model vs previous best Yao et al.Proposed detector · COCO-TextF-score: 0.33 -> 0.37Improved

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