Model card
MATRN.
ResearchunknownUnknown paramsUnknown
Multi-granularity prediction for scene text recognition.
§ 01 · Benchmarks
Every benchmark MATRN has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Union14M | Computer Vision · Scene Text Detection | accuracy | 61.2% | #7 | — | source ↗ |
| 02 | icdar2013 | Computer Vision · Optical Character Recognition | accuracy | 97.9% | #8 | 2021-11-30 | source ↗ |
| 03 | svtp | Computer Vision · Scene Text Recognition | accuracy | 90.6% | #11 | 2021-11-30 | source ↗ |
| 04 | cute80 | Computer Vision · Scene Text Recognition | accuracy | 93.5% | #12 | 2021-11-30 | source ↗ |
| 05 | icdar2015 | Computer Vision · Optical Character Recognition | accuracy | 86.6% | #13 | 2021-11-30 | source ↗ |
| 06 | iiit5k | Computer Vision · Scene Text Recognition | accuracy | 96.6% | #15 | 2021-11-30 | source ↗ |
| 07 | svt | Computer Vision · Scene Text Recognition | accuracy | 95.0% | #16 | 2021-11-30 | 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 MATRN.
- 2021-11-30· Computer Vision· 6 results
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
§ 04 · Related models
Other Research models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
papers-with-code
6
results
arxiv
1
result
6 of 7 rows marked verified.