From 2b3225f599193dbb093fdd627cf612f913b8dd5d Mon Sep 17 00:00:00 2001
From: Emiliana <38952746+emilianavt@users.noreply.github.com>
Date: Sat, 1 Jun 2024 00:17:08 +0200
Subject: [PATCH] Updated video link.

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 9b0102b..4d17be5 100644
--- a/README.md
+++ b/README.md
@@ -18,7 +18,7 @@ Since the landmarks used by OpenSeeFace are a bit different from those used by o
 
 From general observation, OpenSeeFace performs well in adverse conditions (low light, high noise, low resolution) and keeps tracking faces through a very wide range of head poses with relatively high stability of landmark positions. Compared to MediaPipe, OpenSeeFace landmarks remain more stable in challenging conditions and it accurately represents a wider range of mouth poses. However, tracking of the eye region can be less accurate.
 
-I ran OpenSeeFace on a sample clip from the video presentation for [3D Face Reconstruction with Dense Landmarks](https://microsoft.github.io/DenseLandmarks/) by Wood et al. to compare it to MediaPipe and their approach. You can watch the result [here](https://cdn.discordapp.com/attachments/720652345540870237/1016320201807106118/OSFMediaPipe3DFR.mp4).
+I ran OpenSeeFace on a sample clip from the video presentation for [3D Face Reconstruction with Dense Landmarks](https://microsoft.github.io/DenseLandmarks/) by Wood et al. to compare it to MediaPipe and their approach. You can watch the result [here](https://www.vseeface.icu/assets/media/OSFMediaPipe3DFR.mp4).
 
 # Usage