Model card
SVTRv2-B.
Du et al.open-sourceUnknown paramsSVTR Base + Multi-Size Resizing + Feature Rearrangement + Semantic Guidance (CTC)
SVTRv2 Base variant. Best performing. CTC-based, surpasses encoder-decoder models. ICCV 2025. arxiv:2411.15858.
§ 01 · Benchmarks
Every benchmark SVTRv2-B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | icdar-2013 | Computer Vision · Scene Text Detection | accuracy | 98.7% | #5 | 2024-11-24 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Papers
1 paper with results for SVTRv2-B.
- 2024-11-24· Computer Vision· 1 result
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition
§ 04 · Related models
Other Du et al. models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.