AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes

Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai

ECCV 2018 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 539 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 the character-map subnet (joint detection and recognition training) (ablation)Mask TextSpotter · ICDAR2013 detectionF-measure: 91.0 -> 91.7Improved
add the character-map subnet (joint detection and recognition training) (ablation)Mask TextSpotter · ICDAR2015 detectionF-measure: 83.4 -> 86.0Improved
add a few real-world character annotations (ablation)Mask TextSpotter · ICDAR2015 end-to-end, strongF-measure: 76.6 -> 79.3Improved
add a few real-world character annotations (ablation)Mask TextSpotter · ICDAR2013 end-to-endF-measure: 0.7%-2.3%Improved
use weighted edit distance instead of original edit distance (ablation)Mask TextSpotter · ICDAR2015 end-to-end, genericF-measure: 56.7 -> 62.4Improved
use weighted edit distance instead of original edit distance (ablation)Mask TextSpotter · ICDAR2015 end-to-end, weakF-measure: 67.1 -> 73.0Improved
increase input scale from 720 to 1600Mask TextSpotter · ICDAR2015 end-to-end, strongF-measure: 71.3 -> 79.3Improved
increase input scale from 720 to 1600Mask TextSpotter · ICDAR2015FPS: 6.9 -> 2.6Hurt
use Mask TextSpotter instead of Liao et al. on curved textLiao et al. · Total-Text end-to-end, no lexiconF-measure: 36.3 -> 52.9Improved
use Mask TextSpotter instead of Li et al. on ICDAR2013 generic lexiconLi et al. · ICDAR2013 word spotting, strongF-measure: 94.2 -> 92.5No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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