Model card
LRANet++.
Academiccomputer-visionLow-Rank Approximation Network
LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting. IEEE TPAMI 2025. arXiv:2511.05818
§ 01 · Benchmarks
Every benchmark LRANet++ 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 | 83.5% | #3 | — | source ↗ |
| 02 | inverse-text | Computer Vision · Optical Character Recognition | f-measure-no-lexicon | 75.3% | #4 | — | 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.
§ 04 · Related models
Other Academic models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.