Update README.md

README.md

@@ -8,13 +8,13 @@ Gaze following and social gaze prediction are fundamental tasks providing insigh
 
 ## Overview
 
-* **Training**: MTGS-static-vsgaze was trained on [VSGaze]((https://www.idiap.ch/dataset/vsgaze)
+* **Training**: MTGS-static-vsgaze was trained on [VSGaze](https://www.idiap.ch/dataset/vsgaze)
 * **Backbone**: MTGS-static-vsgaze is adapted from [MTGS-static-gazefollow](https://huggingface.co/Idiap/mtgs-static-gazefollow)
   * License: [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/deed.en)
 * **Parameters**: 155M
 * **Task**: MTGS performs multi-person gaze following and social gaze prediction in images and videos. Given an image or a video frame with multiple people, the model predicts where each person is looking in the scene (gaze following) and infers pair-wise social gaze interactions among individuals (social gaze prediction). Specifically, we tackle three social gaze prediction tasks:
   1. Looking at Heads (LAH): whether a person is looking at another person's head.
-  2. Looking at Each Other (LEO): whether two people are looking at each other.
+  2. Looking at Each Other (LAEO): whether two people are looking at each other.
   3. Shared Attention (SA): whether two people are looking at the same target in the scene.
 * **Framework**: PyTorch Lightning