Model card
ABINet-LV.
Fang et al.open-sourceUnknown paramsResNet + Bidirectional Language Model (LV)
ABINet Language-Vision model from CVPR 2021. arxiv:2103.04049.
§ 01 · Benchmarks
Every benchmark ABINet-LV has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | icdar-2013 | Computer Vision · Scene Text Detection | accuracy | 97.0% | #14 | 2021-03-06 | source ↗ |
| 02 | svtp | Computer Vision · Scene Text Recognition | accuracy | 89.5% | #15 | 2021-03-06 | source ↗ |
| 03 | iiit5k | Computer Vision · Scene Text Recognition | accuracy | 96.4% | #17 | 2021-03-06 | source ↗ |
| 04 | cute80 | Computer Vision · Scene Text Recognition | accuracy | 89.2% | #18 | 2021-03-06 | source ↗ |
| 05 | svt | Computer Vision · Scene Text Recognition | accuracy | 93.4% | #22 | 2021-03-06 | 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 ABINet-LV.
- 2021-03-06· Computer Vision· 5 results
Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
§ 04 · Related models
Other Fang et al. models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
5
results
5 of 5 rows marked verified.