Research map / Detection and segmentation / CNN features
ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network
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 |
|---|---|---|---|
| Use BezierAlign instead of horizontal sampling (ablation) | ABCNet · Total-Text test | F-measure: 38.4 -> 61.9 | Helped |
| Use BezierAlign instead of quadrilateral sampling (ablation) | ABCNet · Total-Text test | F-measure: 44.7 -> 61.9 | Helped |
| Use BezierAlign sampling points (7, 32) rather than (6, 32) (ablation) | ABCNet · Total-Text test | F-measure: 59.6 -> 61.9 | Helped |
| Increase BezierAlign sampling points from (7, 32) to (14, 64) (ablation) | ABCNet · Total-Text test | F-measure: 61.9 -> 58.1 | Hurt |
| Increase BezierAlign sampling points from (7, 32) to (21, 96) (ablation) | ABCNet · Total-Text test | F-measure: 61.9 -> 54.8 | Hurt |
| Increase BezierAlign sampling points from (7, 32) to (28, 128) (ablation) | ABCNet · Total-Text test | F-measure: 61.9 -> 53.4 | Hurt |
| Vary BezierAlign sampling points from (7, 32) to (30, 30) (ablation) | ABCNet · Total-Text test | F-measure: 61.9 -> 59.9 | Hurt |
| Include Bezier curve detection (ablation) | ABCNet · Total-Text test | FPS: 22.8 -> 22.5 | Hurt |
| Use multi-scale testing instead of single-scale inference | ABCNet · Total-Text test | F-measure (None): 64.2 -> 69.5 | Helped |
| Use multi-scale testing instead of single-scale inference | ABCNet · Total-Text test | FPS: 17.9 -> 6.9 | Hurt |
| Use short input size 600 for the faster variant | ABCNet · Total-Text test | FPS: 17.9 -> 22.8 | Helped |
| Use ABCNet instead of TextDragon | scene text spotting · CTW1500 test (lexicon-free) | F-measure (None): 39.7 -> 45.2 | Helped |
Closest papers by meaning
- ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection (CVPR 2020 · similarity 0.89)
- Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation (CVPR 2019 · similarity 0.88)
- Towards Robust Curve Text Detection With Conditional Spatial Expansion (CVPR 2019 · similarity 0.88)
- LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network (AAAI 2024 · similarity 0.86)
- Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction (CVPR 2024 · similarity 0.86)
- Bridging the Gap Between End-to-End and Two-Step Text Spotting (CVPR 2024 · similarity 0.85)
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.