---
language:
- en
license: apache-2.0
tags:
- image-to-text
---

# ABINet-LV v1.0

ABINet model pre-trained on various real [STR datasets](https://github.com/baudm/parseq/blob/main/Datasets.md) at image size 128x32.

Disclaimer: this model card was not written by the original authors.

## Model description

*TODO*

## Intended uses & limitations

You can use the model for STR on images containing Latin characters (62 case-sensitive alphanumeric + 32 punctuation marks).

### How to use

*TODO*

### BibTeX entry and citation info

```bibtex
@InProceedings{Fang_2021_CVPR,
    author    = {Fang, Shancheng and Xie, Hongtao and Wang, Yuxin and Mao, Zhendong and Zhang, Yongdong},
    title     = {Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {6},
    year      = {2021},
    pages     = {7098-7107}
}
```