AI Paper Atlas

Research map / Detection and segmentation / CNN features

Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning

Yipeng Sun, Jiaming Liu, Wei Liu, Junyu Han, Errui Ding, Jingtuo Liu

ICCV 2019 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 57 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 400K weakly annotated images with online proposal matching (partially supervised learning) (ablation)End2End · C-SVT testend-to-end F-score: 28.58 -> 33.88Improved
add 400K weakly annotated images with online proposal matching (ablation)End2End · C-SVT testend-to-end AED: 19.68 -> 17.59Improved
add 400K weak annotations instead of equal-cost 4.4K extra full annotations (ablation)End2End · C-SVT testend-to-end F-score: 29.85 -> 33.88Improved
increase weak annotations from 25K to 400K (ablation)End2End-PSL · C-SVT testend-to-end F-score: 31.46 -> 33.88Improved
add 400K weak annotations to ICDAR 2017-RCTW training (ablation)End2End · ICDAR 2017-RCTWend-to-end AED: 27.5 -> 24.2Improved
add 400K weak annotations with multi-scale testing (ablation)End2End-MS · ICDAR 2017-RCTWend-to-end AED: 26.2 -> 22.1Improved
add 400K weak annotations (ablation)End2End · ICDAR 2017-RCTWdetection F-score: 60.1 -> 60.2No clear effect
add 400K weak annotations (ablation)End2end recognition branch · C-SVT test (GT boxes)recognition accuracy: 40.20 -> 48.33Improved
raise OPM threshold tau from 0.05 to 0.2 (ablation)OPM · 500 weak images, IoU 0.5recall: 45 -> 66Improved
raise OPM threshold tau from 0.05 to 0.2 (ablation)OPM · 500 weak images, IoU 0.5precision: 98 -> 92Hurt
add 400K weak annotations on English data (COCO-Text) (ablation)End2End · ICDAR 2015 end-to-end weak lexiconF-score: 75.09 -> 76.25Improved
train with C-SVT full annotations instead of CTWEnd2End · ICDAR 2017-RCTWend-to-end AED: 33.6 -> 26.8Improved

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