Hi, pyschopa4, thanks for your good work!
I have a question about your nonlocal module from fig4 in the paper.
F in the figure is HW/(r^2) x HW/(r^2), which after softmax will multiply Y, so F contains spatial correlation only, because temporal channel is used as feature channel.
So, How does this module model motion between temporal frames? It seems to me temporal weights remain same for all temporal frames because F contains no temporal info.
Hi, pyschopa4, thanks for your good work! I have a question about your nonlocal module from fig4 in the paper.
F in the figure is HW/(r^2) x HW/(r^2), which after softmax will multiply Y, so F contains spatial correlation only, because temporal channel is used as feature channel.
So, How does this module model motion between temporal frames? It seems to me temporal weights remain same for all temporal frames because F contains no temporal info.