Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apple-ascl
|
| 3 |
+
datasets:
|
| 4 |
+
- graph-based-captions/GBC10M
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
### Graph-based captioning (GBC) is a new image annotation paradigm that combines the strengths of long captions, region captions, and scene graphs
|
| 10 |
+
|
| 11 |
+
GBC interconnects region captions to create a unified description akin to a long caption, while also providing structural information similar to scene graphs.
|
| 12 |
+

|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
### Text-to-Image with GBC as Middleware
|
| 16 |
+
|
| 17 |
+
We propose to use GBC as middleware for text-to-image generation. This repository provides model for generating GBC annotation from simple text prompt.
|
| 18 |
+

|
| 19 |
+
|
| 20 |
+
For futher detail on how to use the model please refer to the [accompanying code repository](https://github.com/apple/ml-gbc?tab=readme-ov-file#-gbc-text-to-image).
|
| 21 |
+
|
| 22 |
+
### License
|
| 23 |
+
|
| 24 |
+
For license please checkout the [LICENSE](LICENSE) file.
|
| 25 |
+
|
| 26 |
+
### Citation
|
| 27 |
+
|
| 28 |
+
```
|
| 29 |
+
@article{GBC2024,
|
| 30 |
+
title={Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions},
|
| 31 |
+
author={Yu-Guan Hsieh and Cheng-Yu Hsieh and Shih-Ying Yeh and Louis Béthune and Hadi Pouransari and Pavan Kumar Anasosalu Vasu and Chun-Liang Li and Ranjay Krishna and Oncel Tuzel and Marco Cuturi},
|
| 32 |
+
journal={arXiv preprint arXiv:2407.06723},
|
| 33 |
+
year={2024}
|
| 34 |
+
}
|