diff --git a/doc/running_mccnn.rst b/doc/running_mccnn.rst
index 47ee3473de3c24bc789c5a5420e4ac3ce66410d4..caa89385f305136b332694d96379160cfc1c8798 100644
--- a/doc/running_mccnn.rst
+++ b/doc/running_mccnn.rst
@@ -112,6 +112,3 @@ Using pretrained models
     platforms, versions of pytorch, non-deterministic nature in GPUs and so on. You can go through the follwing link on how to achive best reproducibility
     in PyTorch `PyTorch Reproducibility <https://pytorch.org/docs/stable/notes/randomness.html>`_. If you wish to reproduce the exact same results in the paper, we suggest 
     you to use the pretrained models shipped with the package.
-
-
-.. [GMGNAM19] *A. George, Z. Mostaani, D. Geissenbuhler, O. Nikisins, A. Anjos, S. Marcel*, **Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network**,in: IEEE Transactions on Information Forensics & Security, 2019 (Accepted).
\ No newline at end of file