Research map / Detection and segmentation / CNN features
Fourier Contour Embedding for Arbitrary-Shaped Text Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 text center region loss when regression loss is enabled (ablation) | FCENet · CTW1500 | F-measure: 81.3 -> 85.5 | Helped |
| Add text center region loss when regression loss is enabled (ablation) | FCENet · Total-Text | F-measure: 78.6 -> 85.8 | Helped |
| Add regression loss when text center region loss is enabled (ablation) | FCENet · CTW1500 | F-measure: 78.6 -> 85.5 | Helped |
| Add regression loss when text center region loss is enabled (ablation) | FCENet · Total-Text | F-measure: 76.5 -> 85.8 | Helped |
| Add text center region loss without regression loss (ablation) | FCENet · CTW1500 | F-measure: 77.1 -> 78.6 | Helped |
| Add text center region loss without regression loss (ablation) | FCENet · Total-Text | F-measure: 76.1 -> 76.5 | Helped |
| Add regression loss without text center region loss (ablation) | FCENet · CTW1500 | F-measure: 77.1 -> 81.3 | Helped |
| Add regression loss without text center region loss (ablation) | FCENet · Total-Text | F-measure: 76.1 -> 78.6 | Helped |
| Add DCN to the ResNet50 backbone (ablation) | FCENet · CTW1500 | F-measure: 83.1 -> 85.5 | Helped |
| Add DCN to the ResNet50 backbone (ablation) | FCENet · Total-Text | F-measure: 83.4 -> 85.8 | Helped |
| Use Fourier contour embedding rather than TextRay contour representation | Text detection on the CTW1500 highly-curved subset · CTW1500 highly-curved subset | F-measure: 74.0 -> 79.2 | Helped |
| Use FCENet instead of DB | Text detection · ICDAR2015 | F-measure: 87.3 -> 86.2 | Hurt |
Closest papers by meaning
- ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection (CVPR 2020 · similarity 0.89)
- Progressive Contour Regression for Arbitrary-Shape Scene Text Detection (CVPR 2021 · similarity 0.88)
- Shape Robust Text Detection With Progressive Scale Expansion Network (CVPR 2019 · similarity 0.88)
- LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network (AAAI 2024 · similarity 0.88)
- Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction (CVPR 2024 · similarity 0.83)
- Towards Unified Multi-granularity Text Detection with Interactive Attention (ICML 2024 · similarity 0.83)
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.