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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add end-to-end joint training of detection and recognition (ablation) | TextDragon · CTW1500 detection | F-measure: 80.2 -> 83.6 | Improved |
| add end-to-end joint training of detection and recognition (ablation) | TextDragon · CTW1500 end-to-end None | F-measure: 37.2 -> 39.7 | Improved |
| add end-to-end joint training of detection and recognition (ablation) | TextDragon · CTW1500 end-to-end Full | F-measure: 69.9 -> 72.4 | Improved |
| add end-to-end joint training of detection and recognition (ablation) | TextDragon · Total-Text detection | F-measure: 79.0 -> 80.3 | Improved |
| add end-to-end joint training of detection and recognition (ablation) | TextDragon · Total-Text end-to-end None | F-measure: 46.1 -> 48.8 | Improved |
| add end-to-end joint training of detection and recognition (ablation) | TextDragon · Total-Text end-to-end Full | F-measure: 70.6 -> 74.8 | Improved |
| add end-to-end joint training of detection and recognition (ablation) | TextDragon · ICDAR 2015 end-to-end Strong | F-measure: 75.23 -> 82.54 | Improved |
| use RoISlide instead of RoIRotate for curved text (ablation) | TextDragon · CTW1500 end-to-end None | F-measure: 38.6 -> 39.7 | Improved |
| use RoISlide instead of RoIRotate for curved text (ablation) | TextDragon · Total-Text end-to-end Full | F-measure: 73.6 -> 74.8 | Improved |
| use RoISlide instead of RoIRotate on oriented text (ablation) | TextDragon · ICDAR 2015 end-to-end Strong | F-measure: 82.51 -> 82.54 | No clear effect |
| add bi-directional LSTM to the recognizer (ablation) | TextDragon · CTW1500 end-to-end None | F-measure: 39.7 -> 39.2 | No clear effect |
| add bi-directional LSTM to the recognizer (ablation) | TextDragon · Total-Text end-to-end Full | F-measure: 74.8 -> 74.7 | No 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.
- PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network (AAAI 2021 · better on 0 of 2 shared results)
- MANGO: A Mask Attention Guided One-Stage Scene Text Spotter (AAAI 2021 · better on 1 of 1 shared result)
- PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond (TPAMI 2021 · better on 1 of 1 shared result)
- Towards End-to-End Text Spotting in Natural Scenes (TPAMI 2021 · better on 0 of 1 shared result)
- ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network (CVPR 2020 · better on 2 of 2 shared results)
- Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting (ECCV 2020 · better on 2 of 2 shared results)
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.
- FOTS — FOTS: Fast Oriented Text Spotting With a Unified Network (CVPR 2018) · better on 4 of 6 shared results
- TextSnake — TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (ECCV 2018) · better on 2 of 2 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
- Towards Unconstrained End-to-End Text Spotting (ICCV 2019 · similarity 0.92)
- Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting (AAAI 2020 · similarity 0.91)
- LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting (TPAMI 2026 · similarity 0.90)
- All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting (AAAI 2020 · similarity 0.90)
- LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network (AAAI 2024 · similarity 0.86)
- Bridging the Gap Between End-to-End and Two-Step Text Spotting (CVPR 2024 · similarity 0.86)
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.
