Research map / Vision-language and multimodal / Human and embodied modeling
Context-Based Contrastive Learning for Scene Text Recognition
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 |
|---|---|---|---|
| Add ConCLR to ABINet | ABINet · IIIT5K | accuracy: 95.7 -> 96.5 | Helped |
| Add ConCLR to ABINet | ABINet · IC13 | accuracy: 97.7 -> 97.7 | No clear effect |
| Add ConCLR to ABINet | ABINet · SVT | accuracy: 93.9 -> 94.3 | Helped |
| Add ConCLR to ABINet | ABINet · IC15 | accuracy: 84.9 -> 85.4 | Hurt |
| Add ConCLR to ABINet | ABINet · SVTP | accuracy: 88.5 -> 89.3 | Helped |
| Add ConCLR to ABINet | ABINet · CUTE | accuracy: 87.5 -> 91.3 | Helped |
| Add ConAug and contrastive loss | ABINet-Vision · OutText | accuracy: 63.2 -> 67.7 | Helped |
| Use ConAug without contrastive loss (ablation) | ABINet-Vision · OutText | accuracy: 63.2 -> 64.8 | Helped |
| Add contrastive loss to ConAug training (ablation) | ABINet-Vision · OutText | accuracy: 64.8 -> 67.7 | Helped |
| Use SingleCat rather than RandCat concatenation (ablation) | ConCLR · OutText | accuracy: 67.7 -> 66.3 | Hurt |
| Use FixCat rather than RandCat concatenation (ablation) | ConCLR · OutText | accuracy: 67.7 -> 67.2 | Hurt |
| Add ConCLR to ABINet-Vision | ABINet-Vision · six public datasets (AVG) | accuracy: 89.8 -> 91.4 | Helped |
Closest papers by meaning
- Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing (NeurIPS 2024 · similarity 0.89)
- CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR (CVPR 2025 · similarity 0.87)
- Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition (CVPR 2025 · similarity 0.87)
- Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models (CVPR 2024 · similarity 0.87)
- OTE: Exploring Accurate Scene Text Recognition Using One Token (CVPR 2024 · similarity 0.86)
- ConText: Driving In-context Learning for Text Removal and Segmentation (ICML 2025 · similarity 0.86)
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.