Research map / Vision-language and multimodal / Human and embodied modeling
On Vocabulary Reliance in Scene Text Recognition
Zhaoyi Wan, Jielei Zhang, Liang Zhang, Jiebo Luo, Cong Yao
Check 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 mutual learning with a segmentation-based decoder | Attention decoder · Scene text recognition evaluation framework | vocabulary generalization (VG): 77.1 to 93.6 | Improved |
| Add mutual learning with an attention-based decoder | Segmentation-based decoder · Scene text recognition evaluation framework | vocabulary learning ability (VA): 75.8 to 82.3 | Improved |
| Mix RS data into LS training data at ratio 25% (ablation) | Attention decoder without context module · IIIT | accuracy: 77.8% to 84.4% | Improved |
| Add PPM context modeling (ablation) | Segmentation-based decoder · Scene text recognition evaluation framework | vocabulary learning ability (VA): +3.9% | Improved |
| Add PPM context modeling (ablation) | CTC decoder · Scene text recognition evaluation framework | vocabulary learning ability (VA): +10.5% | Improved |
| Add context modeling (ablation) | CTC-family models · Scene text recognition evaluation framework | vocabulary generalization (VG) | Hurt |
| Add BLSTM context modeling (ablation) | Attention decoder · Scene text recognition evaluation framework | general accuracy (GA): 81.0 to 83.1 | Improved |
| Add mutual learning with an attention-based decoder (ablation) | Segmentation-based decoder · Scene text recognition evaluation framework | vocabulary generalization (VG): 97.3 to 96.0 | Hurt |
Closest papers by meaning
- Revisiting Scene Text Recognition: A Data Perspective (ICCV 2023 · similarity 0.90)
- What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis (ICCV 2019 · similarity 0.88)
- Towards Open Vocabulary Learning: A Survey (TPAMI 2024 · similarity 0.88)
- OTE: Exploring Accurate Scene Text Recognition Using One Token (CVPR 2024 · similarity 0.88)
- Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition (CVPR 2025 · similarity 0.87)
- Image as a Language: Revisiting Scene Text Recognition via Balanced, Unified and Synchronized Vision-Language Reasoning Network (AAAI 2024 · 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.
