Research map / Detection and segmentation / CNN features
FOTS: Fast Oriented Text Spotting With a Unified Network
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 |
|---|---|---|---|
| Train detection and recognition jointly with shared convolutional features instead of training them separately (ablation) | FOTS · ICDAR 2015 | Strong lexicon end-to-end F-measure: 77.11 -> 81.09 | Helped |
| Train detection and recognition jointly with shared convolutional features instead of training them separately (ablation) | FOTS · ICDAR 2015 | Detection F-measure: 85.31 -> 87.99 | Helped |
| Train detection and recognition jointly with shared convolutional features instead of training them separately (ablation) | FOTS · ICDAR 2013 | Strong lexicon word spotting F-measure: 82.97 -> 83.51 | Helped |
| Use multi-scale testing (ablation) | FOTS · ICDAR 2015 | Detection F-measure: 87.99 -> 89.84 | Helped |
| Use multi-scale testing (ablation) | FOTS · ICDAR 2017 MLT | Detection F-measure: 67.25 -> 70.75 | Helped |
| Use multi-scale testing (ablation) | FOTS · ICDAR 2013 | IC03 F-measure: 88.23 -> 92.50 | Helped |
| Replace ResNet-50 with ResNet-34 and use 1280×720 input (ablation) | FOTS · ICDAR 2015 | Detection F-measure: 87.99 -> 82.78 | Hurt |
| Replace ResNet-50 with ResNet-34 and use 1280×720 input (ablation) | FOTS · ICDAR 2015 | End-to-end speed: 7.5 fps -> 22.6 fps | Helped |
| Apply online hard example mining (ablation) | FOTS detection branch · ICDAR 2015 | F-measure: about 2% | Helped |
| Share convolutional features and perform recognition in the same network rather than using separate systems (ablation) | FOTS · ICDAR 2015 | Parameters: 63.90 M -> 34.98 M | Helped |
Closest papers by meaning
- Bridging the Gap Between End-to-End and Two-Step Text Spotting (CVPR 2024 · similarity 0.86)
- DeepSolo: Let Transformer Decoder With Explicit Points Solo for Text Spotting (CVPR 2023 · similarity 0.86)
- Deep Matching Prior Network: Toward Tighter Multi-Oriented Text Detection (CVPR 2017 · similarity 0.86)
- SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting (CVPR 2025 · similarity 0.85)
- ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting (CVPR 2024 · similarity 0.84)
- GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching (NeurIPS 2024 · similarity 0.84)
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.