OpenFace-CQUPT
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
# FLIP (Facial Language Image Pretrain)
|
2 |
|
3 |
-
This repository is the official implementation of [FaceCaption-15M](
|
4 |
|
5 |
**Overview of FLIP architecture.**
|
6 |
|
@@ -22,7 +22,7 @@ We provide pretrained model weights for the [vit base version](https://huggingfa
|
|
22 |
|
23 |
## Datasets
|
24 |
|
25 |
-
|
26 |
|
27 |
**Overview of our proposed FaceCaption-15M containing over 15 million facial image-text (right and left) pairs.**
|
28 |
|
|
|
1 |
# FLIP (Facial Language Image Pretrain)
|
2 |
|
3 |
+
This repository is the official implementation of [FaceCaption-15M]().
|
4 |
|
5 |
**Overview of FLIP architecture.**
|
6 |
|
|
|
22 |
|
23 |
## Datasets
|
24 |
|
25 |
+
Download the FaceCaption-15M dataset from [here](https://huggingface.co/datasets/OpenFace-CQUPT/FaceCaption-15M).
|
26 |
|
27 |
**Overview of our proposed FaceCaption-15M containing over 15 million facial image-text (right and left) pairs.**
|
28 |
|