Model card
SwinTextSpotter v2.
Academiccomputer-visionSwin Transformer, improved detection-recognition synergy
SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting. IJCV 2025. arXiv:2401.07641
§ 02 · Benchmarks
Every benchmark SwinTextSpotter v2 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | inverse-text | Computer Vision · Optical Character Recognition | f-measure-full-lexicon | 76.5% | #7 | — | source ↗ |
| 02 | inverse-text | Computer Vision · Optical Character Recognition | f-measure-no-lexicon | 64.8% | #8 | — | 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 · Strengths by area
Where SwinTextSpotter v2 actually performs.
§ 05 · Related models
Other Academic models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.