AI Paper Atlas

Research map / Detection and segmentation / CNN features

Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning

Jingqun Tang, Wenming Qian, Luchuan Song, Xiena Dong, Lan Li, Xiang Bai

ECCV 2022 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 22 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
train with BoxDQN-adjusted boxesEAST+CRNN · IC15F-score: 82.2 -> 83.9Improved
train with BoxDQN-adjusted boxesEAST+CRNN · MLT19F-score: 53.9 -> 56.9Improved
train with BoxDQN-adjusted boxestwo-step pipelines · IC13, IC15, MLT19, ReCTSF-score gain: at least 1.6%Improved
train with BoxDQN-adjusted boxesABCNet · MLT19F-score: 56.2 -> 59.5Improved
train with BoxDQN-adjusted boxesMTS-V3 · MLT19F-score: 61.2 -> 64.0Improved
train with BoxDQN-adjusted boxesFOTS · IC15F-score: 81.5 -> 83.3Improved
adjust pseudo-labels with BoxDQN for synthetic-to-real adaptationEAST+CRNN · MLT19 (cross-domain)F-score: 41.3 -> 48.3Improved
adjust pseudo-labels with BoxDQN for synthetic-to-real adaptationMTS-V3 · IC15 (cross-domain)F-score: 71.3 -> 76.0Improved
use BoxDQN instead of grid search (ablation)EAST+CRNN · IC15F-score: 82.8 -> 83.9Improved
use BoxDQN instead of grid search (ablation)MTS-V3 · IC15F-score: 83.4 -> 84.5Improved
add background image and box coordinates to the DQN input via FFM (ablation)DBNET+RARE · IC15F-score: 85.7 -> 86.3Improved
add background image and box coordinates to the DQN input via FFM (ablation)MTS-V3 · IC15F-score: 83.8 -> 84.5Improved

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