update citations to match the linked whitepaper (#3127)

* update citations

* use original submission year

---------

Co-authored-by: vfdev <[email protected]>

Author: djwadhwa

examples/super_resolution/README.md

@@ -2,7 +2,7 @@
 
 ported from [pytorch-examples](https://github.com/pytorch/examples/tree/main/super_resolution)
 
-This example illustrates how to use the efficient sub-pixel convolution layer described in ["Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network" - Shi et al.](https://arxiv.org/abs/1609.05158) for increasing spatial resolution within your network for tasks such as superresolution.
+This example illustrates how to use the efficient sub-pixel convolution layer described in ["Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network" - Shi et al. 2016](https://arxiv.org/abs/1609.05158) for increasing spatial resolution within your network for tasks such as superresolution.
 
 ```
 usage: main.py [-h] --upscale_factor UPSCALE_FACTOR [--crop_size CROPSIZE] [--batch_size BATCHSIZE]

ignite/metrics/gan/fid.py

@@ -62,11 +62,11 @@ class FID(_BaseInceptionMetric):
     where :math:`\mu_1` and :math:`\sigma_1` refer to the mean and covariance of the train data and
     :math:`\mu_2` and :math:`\sigma_2` refer to the mean and covariance of the test data.
 
-    More details can be found in `Heusel et al. 2002`__
+    More details can be found in `Heusel et al. 2017`__
 
     __ https://arxiv.org/pdf/1706.08500.pdf
 
-    In addition, a faster and online computation approach can be found in `Chen et al. 2014`__
+    In addition, a faster and online computation approach can be found in `Mathiasen et al. 2020`__
 
     __ https://arxiv.org/pdf/2009.14075.pdf