Update README.md

README.md

@@ -6,8 +6,8 @@ base_model:
 
 <h1 align="center">AVF-MAE++ : Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning</h1>
 
-> [Xuecheng Wu](https://scholar.google.com.hk/citations?user=MuTEp7sAAAAJ), [Heli Sun](https://scholar.google.com.hk/citations?user=HXjwuE4AAAAJ), Yifan Wang, Jiayu Nie, [Jie Zhang](https://scholar.google.com.hk/citations?user=7YkR3CoAAAAJ), [Yabing Wang](https://scholar.google.com.hk/citations?user=3WVFdMUAAAAJ), [Junxiao Xue](https://scholar.google.com.hk/citations?user=Za9YFVIAAAAJ), Liang He<br>
-> Xi'an Jiaotong University & University of Science and Technology of China & A*STAR & Zhejiang Lab<br>
+[Xuecheng Wu](https://scholar.google.com.hk/citations?user=MuTEp7sAAAAJ), [Heli Sun](https://scholar.google.com.hk/citations?user=HXjwuE4AAAAJ), Yifan Wang, Jiayu Nie, [Jie Zhang](https://scholar.google.com.hk/citations?user=7YkR3CoAAAAJ), [Yabing Wang](https://scholar.google.com.hk/citations?user=3WVFdMUAAAAJ), [Junxiao Xue](https://scholar.google.com.hk/citations?user=Za9YFVIAAAAJ), Liang He<br>
+Xi'an Jiaotong University & University of Science and Technology of China & A*STAR & Zhejiang Lab<br>
 
 
 
@@ -20,19 +20,19 @@ base_model:
 ## 🛫 Main Results
 
 <p align="center">
-  <img src="figs/radar_1030.png" width=45%> <br>
+  <img src="figs/radar_1030.png" width=55%> <br>
    Performance comparisons of AVF-MAE++ and state-of-the-art AVFA methods on 17 datasets across CEA, DEA, and MER tasks.
 </p>
 
 
 <p align="center">
-  <img src="figs/CEA-DEA.jpg" width=65%> <br>
+  <img src="figs/CEA-DEA.jpg" width=75%> <br>
    Performance comparisons of AVF-MAE++ with state-of-the-art CEA and DEA methods on twelve datasets.
 </p>
 
 
 <p align="center">
-  <img src="figs/MER.jpg" width=35%> <br>
+  <img src="figs/MER.jpg" width=55%> <br>
    Performance comparisons of AVF-MAE++ and state-ofthe-art MER methods in terms of UF1 (%) on five datasets
 </p>