Update README.md

README.md

@@ -22,7 +22,9 @@ by **Soufiane Belharbi<sup>1</sup>, Marco Pedersoli<sup>1</sup>, Alessandro Lame
 
 <p align="center"><img src="promo.png" alt="outline" width="60%"></p>
 
-## ArXiv: [2402.00281](https://arxiv.org/pdf/2402.00281.pdf)
+
+[![arXiv](https://img.shields.io/badge/arXiv-2402.00281-b31b1b.svg)](https://arxiv.org/abs/2402.00281)
+[![Github](https://img.shields.io/badge/github-interpretable--fer--aus-brightgreen.svg)](https://github.com/sbelharbi/interpretable-fer-aus)
 
 ## Abstract
 Although state-of-the-art classifiers for facial expression recognition (FER) can achieve a high level of accuracy, they lack interpretability, an important feature for end-users. 
@@ -45,7 +47,6 @@ Our extensive evaluation on two public benchmarks RAFDB, and AFFECTNET datasets
 }
 ```
 
-## Github code: [https://github.com/sbelharbi/interpretable-fer-aus](https://github.com/sbelharbi/interpretable-fer-aus)
 
 ## Pre-trained models:
 This repository contains the pretrained weights for this paper. They are stored in the file [shared-trained-models.tar.gz](https://huggingface.co/sbelharbi/interpretable-fer-aus/resolve/main/shared-trained-models.tar.gz?download=true). The file is 5.7GB.