Research map / Detection and segmentation / CNN features
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
Read the paperCheck 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 |
|---|---|---|---|
| Replace the two-stage pipeline with end-to-end training using STM | Text Perceptron · Total-Text | End-to-End None: 63.3 -> 69.7 | Helped |
| Replace the two-stage pipeline with end-to-end training using STM | Text Perceptron · Total-Text | End-to-End Full: 73.9 -> 78.3 | Helped |
| Replace the two-stage pipeline with end-to-end training using STM | Text Perceptron · CTW1500 | End-to-End None: 48.6 -> 57.0 | Helped |
| Replace the two-stage pipeline with end-to-end training using STM | Text Perceptron · IC15 | End-to-End G: 63.0 -> 65.1 | Helped |
| Increase the number of fiducial points from 4 to 14 (ablation) | Text Perceptron · Total-Text | Detection F-measure: 71.5 -> 85.2 | Helped |
| Increase the number of fiducial points from 4 to 14 (ablation) | Text Perceptron · Total-Text | End-to-end F-measure: 55.9 -> 69.7 | Helped |
| Increase the number of fiducial points from 4 to 14 (ablation) | Text Perceptron · CTW1500 | Detection F-measure: 68.7 -> 84.6 | Helped |
| Increase the number of fiducial points from 4 to 14 (ablation) | Text Perceptron · CTW1500 | End-to-end F-measure: 40.2 -> 57.0 | Helped |
| Increase the number of fiducial points from 4 to 14 (ablation) | Text Perceptron · IC15 | Detection F-measure: 87.1 -> 86.9 | No clear effect |
Closest papers by meaning
- All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting (AAAI 2020 · similarity 0.90)
- Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation (CVPR 2019 · similarity 0.89)
- Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes (CVPR 2019 · similarity 0.88)
- Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition (AAAI 2019 · similarity 0.88)
- LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network (AAAI 2024 · similarity 0.87)
- Bridging the Gap Between End-to-End and Two-Step Text Spotting (CVPR 2024 · similarity 0.87)
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.