Research map / Detection and segmentation / CNN features
Detection and Recognition of Text Embedded in Online Images via Neural Context Models
Chulmoo Kang, Gunhee Kim, Suk Yoo
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 local neighbor-box context to text detection (ablation) | CTSN · Instagram | detection F1: 29.2 -> 55.5 | Improved |
| add local neighbor-box context to text detection (ablation) | CTSN · Flickr | detection F1: 34.0 -> 55.5 | Improved |
| add metadata topic bias (LDA) to word recognition (ablation) | CTSN · Instagram | cropped-word recognition accuracy: 87.3 -> 90.4 | Improved |
| add metadata topic bias (LDA) to word recognition (ablation) | CTSN · Flickr | cropped-word recognition accuracy: 90.3 -> 93.0 | Improved |
| add both detection and recognition context (ablation) | CTSN · Instagram | end-to-end F1: 18.9 -> 43.3 | Improved |
| add both detection and recognition context (ablation) | CTSN · Flickr | end-to-end F1: 20.0 -> 39.7 | Improved |
| use CTSN with context instead of best baseline TER | text detection · Instagram | detection F1: 46.3 -> 55.5 | Improved |
Closest papers by meaning
- Towards End-To-End Text Spotting With Convolutional Recurrent Neural Networks (ICCV 2017 · similarity 0.89)
- Towards End-to-End Text Spotting in Natural Scenes (TPAMI 2021 · similarity 0.88)
- Character Region Awareness for Text Detection (CVPR 2019 · similarity 0.86)
- An End-to-End TextSpotter With Explicit Alignment and Attention (CVPR 2018 · similarity 0.86)
- SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting (CVPR 2025 · similarity 0.85)
- 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.
