From bdf1b4070d1533b1c517d555e0358fc93c1fa791 Mon Sep 17 00:00:00 2001
From: Nataniel Ruiz <nruiz9@gatech.edu>
Date: 星期四, 30 十一月 2017 07:53:49 +0800
Subject: [PATCH] Update README.md

---
 README.md |    7 +++++--
 1 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 5f39618..8946000 100644
--- a/README.md
+++ b/README.md
@@ -6,9 +6,12 @@
 
 **Hopenet** is an accurate and easy to use head pose estimation network. Models have been trained on the 300W-LP dataset and have been tested on real data with good qualitative performance. For accuracy numbers and more details about the method please check the [paper](https://arxiv.org/abs/1710.00925).
 
-**new** [GoT trailer example](https://youtu.be/OZdOrSLBQmI)
 
-[Conan-Cruise-Car](https://youtu.be/Bz6eF4Nl1O8)
+<p align="center"><img src="https://i.imgur.com/pcz14p0.gifv" /></p>
+
+**new** [GoT trailer example video](https://youtu.be/OZdOrSLBQmI)
+
+**new** [Conan-Cruise-Car example video](https://youtu.be/Bz6eF4Nl1O8)
 
 
 To use please install [PyTorch](http://pytorch.org/) and [OpenCV](https://opencv.org/) (for video) - I believe that's all you need apart from usual libraries such as numpy. You need a GPU to run Hopenet (for now).

--
Gitblit v1.8.0