AI Paper Atlas

Research map / Detection and segmentation / CNN features

Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping

Chuhui Xue, Shijian Lu, Fangneng Zhan

ECCV 2018 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 135 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 semantics-aware text borders (ablation)Baseline (ResNet) · MSRA-TD500f-score: 71.8 -> 74.3Improved
add bootstrapping augmentation (ablation)Baseline (ResNet) · MSRA-TD500f-score: 71.8 -> 74.3Improved
add both borders and augmentation (ablation)Border (ResNet) · MSRA-TD500f-score: 74.3 -> 76.8Improved
replace ResNet-50 with DenseNet-121 (ablation)Aug.+Border · MSRA-TD500f-score: 76.8 -> 80.1Improved
add semantics-aware text borders (ablation)Baseline (ResNet) · ICDAR2013f-score: 83.0 -> 84.9Improved
add bootstrapping augmentation (ablation)Baseline (ResNet) · ICDAR2013f-score: 83.0 -> 85.2Improved
add both borders and augmentation (ablation)Baseline (ResNet) · ICDAR2013f-score: 83.0 -> 87.4Improved
replace ResNet-50 with DenseNet-121 (ablation)Aug.+Border · ICDAR2013f-score: 87.4 -> 89.2Improved
add semantics-aware text borders (ablation)Baseline (ResNet) · ICDAR2017-RCTWf-score: 58.5 -> 65.4Improved
add semantics-aware text borders (ablation)Baseline (ResNet) · ICDAR2017-MLTf-score: 62.6 -> 66.6Improved
add semantics-aware text borders and augmentation, evaluated at stricter IoU 0.8 vs 0.5 (ablation)Baseline · MSRA-TD500f-score gap vs baseline: 5.0 -> 15.9Improved
add bootstrapping augmentation (faster convergence) (ablation)Baseline (ResNet) · MSRA-TD500training time (hours): 56 -> 36Improved

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