Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- document-layout-analysis
|
| 5 |
+
- yolo
|
| 6 |
+
- object-detection
|
| 7 |
+
base_model: juliozhao/DocLayout-YOLO-DocStructBench
|
| 8 |
+
arxiv: '2410.12628'
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# DocLayout-YOLO-DocStructBench (Fork)
|
| 12 |
+
|
| 13 |
+
**This is a pinned fork of [juliozhao/DocLayout-YOLO-DocStructBench](https://huggingface.co/juliozhao/DocLayout-YOLO-DocStructBench)** for use by [paper-cli](https://github.com/collaborative-deep-research/agent-papers-cli). We pin to a specific snapshot to avoid upstream changes breaking our pipeline.
|
| 14 |
+
|
| 15 |
+
## Original Work
|
| 16 |
+
|
| 17 |
+
All credit for this model goes to the original authors:
|
| 18 |
+
|
| 19 |
+
> **DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception**
|
| 20 |
+
>
|
| 21 |
+
> Zhiyuan Zhao, Hengrui Kang, Bin Wang, Conghui He
|
| 22 |
+
>
|
| 23 |
+
> [arXiv:2410.12628](https://arxiv.org/abs/2410.12628) | [GitHub](https://github.com/opendatalab/DocLayout-YOLO)
|
| 24 |
+
|
| 25 |
+
```bibtex
|
| 26 |
+
@article{zhao2024doclayout,
|
| 27 |
+
title={DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception},
|
| 28 |
+
author={Zhao, Zhiyuan and Kang, Hengrui and Wang, Bin and He, Conghui},
|
| 29 |
+
journal={arXiv preprint arXiv:2410.12628},
|
| 30 |
+
year={2024}
|
| 31 |
+
}
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
## License
|
| 35 |
+
|
| 36 |
+
Apache 2.0 (same as the original).
|