AI Paper Atlas

Research map / Detection and segmentation / CNN features

TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting

Wei Feng, Wenhao He, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu

ICCV 2019 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 236 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 end-to-end joint training of detection and recognition (ablation)TextDragon · CTW1500 detectionF-measure: 80.2 -> 83.6Improved
add end-to-end joint training of detection and recognition (ablation)TextDragon · CTW1500 end-to-end NoneF-measure: 37.2 -> 39.7Improved
add end-to-end joint training of detection and recognition (ablation)TextDragon · CTW1500 end-to-end FullF-measure: 69.9 -> 72.4Improved
add end-to-end joint training of detection and recognition (ablation)TextDragon · Total-Text detectionF-measure: 79.0 -> 80.3Improved
add end-to-end joint training of detection and recognition (ablation)TextDragon · Total-Text end-to-end NoneF-measure: 46.1 -> 48.8Improved
add end-to-end joint training of detection and recognition (ablation)TextDragon · Total-Text end-to-end FullF-measure: 70.6 -> 74.8Improved
add end-to-end joint training of detection and recognition (ablation)TextDragon · ICDAR 2015 end-to-end StrongF-measure: 75.23 -> 82.54Improved
use RoISlide instead of RoIRotate for curved text (ablation)TextDragon · CTW1500 end-to-end NoneF-measure: 38.6 -> 39.7Improved
use RoISlide instead of RoIRotate for curved text (ablation)TextDragon · Total-Text end-to-end FullF-measure: 73.6 -> 74.8Improved
use RoISlide instead of RoIRotate on oriented text (ablation)TextDragon · ICDAR 2015 end-to-end StrongF-measure: 82.51 -> 82.54No clear effect
add bi-directional LSTM to the recognizer (ablation)TextDragon · CTW1500 end-to-end NoneF-measure: 39.7 -> 39.2No clear effect
add bi-directional LSTM to the recognizer (ablation)TextDragon · Total-Text end-to-end FullF-measure: 74.8 -> 74.7No clear effect

Later papers that compared with this method

6 later accepted papers report TextDragon as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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