Update README.md

README.md

@@ -24,21 +24,6 @@ We provide pretrained model weights for the [vit base version](https://huggingfa
 
 Download the FaceCaption-15M dataset from [here](https://huggingface.co/datasets/OpenFace-CQUPT/FaceCaption-15M).
 
-**Overview of our proposed FaceCaption-15M containing over 15 million facial image-text (right and left) pairs.**
-
-![image-20240318100601414](https://img.yutangli.net/img/202403181006981.png)
-
-**Comparisons with other popular facial image datasets.**
-
-![image-20240318100734131](https://img.yutangli.net/img/202403181007778.png)
-
-**Image quality score distribution.**
-
-![image-20240318100849106](https://img.yutangli.net/img/202403181008178.png)
-
-**Text distribution.**
-
-![image-20240318100913176](https://img.yutangli.net/img/202403181009312.png)
 
 ## Results