Research map / Detection and segmentation / CNN features
Single Shot Text Detector With Regional Attention
Pan He, Weilin Huang, Tong He, Qile Zhu, Yu Qiao, Xiaolin Li
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 text attention module (TAM) (ablation) | Baseline SSD-based text detector · ICDAR 2013 (new standard) | F-measure: 0.82 -> 0.85 | Improved |
| add text attention module (TAM) (ablation) | Baseline SSD-based text detector · ICDAR 2013 (new standard) | recall: 0.78 -> 0.83 | Improved |
| add hierarchical inception module (HIM) (ablation) | Baseline SSD-based text detector · ICDAR 2013 (new standard) | F-measure: 0.82 -> 0.84 | Improved |
| add hierarchical inception module (HIM) (ablation) | Baseline SSD-based text detector · ICDAR 2013 (new standard) | recall: 0.78 -> 0.82 | Improved |
| add both TAM and HIM (ablation) | Baseline SSD-based text detector · ICDAR 2013 (new standard) | F-measure: 0.82 -> 0.87 | Improved |
| add both TAM and HIM (ablation) | Baseline SSD-based text detector · ICDAR 2013 (new standard) | precision: 0.87 -> 0.88 | Improved |
| add SSD-based modifications for text word prediction (baseline model vs plain SSD) (ablation) | SSD · ICDAR 2013 (new standard) | F-measure: 0.68 -> 0.82 | Improved |
| add TAM on top of HIM (full model vs HIM only) (ablation) | Baseline SSD-based text detector + HIM · ICDAR 2013 (new standard) | F-measure: 0.84 -> 0.87 | Improved |
| full model vs CTPN under DetEval | Proposed detector · ICDAR 2013 (DetEval) | F-measure: 0.88 -> 0.88 | No clear effect |
| full model vs CTPN on multi-orientation text | Proposed detector · ICDAR 2015 | F-measure: 0.61 -> 0.77 | Improved |
| full model vs previous best Yao et al. | Proposed detector · COCO-Text | F-score: 0.33 -> 0.37 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Textboxes — TextBoxes: A Fast Text Detector with a Single Deep Neural Network (AAAI 2017) · better on 3 of 4 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
- An End-to-End TextSpotter With Explicit Alignment and Attention (CVPR 2018 · similarity 0.90)
- A Text Detection System for Natural Scenes With Convolutional Feature Learning and Cascaded Classification (CVPR 2016 · similarity 0.89)
- EAST: An Efficient and Accurate Scene Text Detector (CVPR 2017 · similarity 0.88)
- Multi-Oriented Text Detection With Fully Convolutional Networks (CVPR 2016 · similarity 0.88)
- Self-Organized Text Detection With Minimal Post-Processing via Border Learning (ICCV 2017 · similarity 0.88)
- Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV 2016 · similarity 0.88)
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.
