From 23d6ddc5a16f3997e4dfdb6414dba4e8da0bf237 Mon Sep 17 00:00:00 2001
From: sniklaus <simon.niklaus@outlook.com>
Date: Mon, 11 Sep 2017 20:15:53 -0700
Subject: no message

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

diff --git a/README.md b/README.md
index 975c4b8..98071ff 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # pytorch-sepconv
 This is a reference implementation of Video Frame Interpolation via Adaptive Separable Convolution [1] using PyTorch. Given two frames, it will make use of <a href="http://graphics.cs.pdx.edu/project/adaconv">adaptive convolution</a> [2] in a separable manner to interpolate the intermediate frame. Should you be making use of our work, please cite our paper [1].
 
-<a href="https://arxiv.org/abs/1703.07514" rel="Paper"><img src="http://content.sniklaus.com/SepConv/Paper.jpg" alt="Paper" width="100%"></a>
+<a href="https://arxiv.org/abs/1708.01692" rel="Paper"><img src="http://content.sniklaus.com/SepConv/Paper.jpg" alt="Paper" width="100%"></a>
 
 For the Torch version of this work, please see: https://github.com/sniklaus/torch-sepconv
 
-- 
cgit v1.2.3-70-g09d2