hshustc

The paper inspires me a lot. Great work! I am wondering when the code will be released. Looking forward to it. Thanks a lot.

When taking videos as input

3

When taking videos input, the feature maps in each layer have four dimensions, i.e., T*H*W*C. Are the attention maps are still query-independent? Could you please give more details? Thanks a...

I found that in some implementations of GAN, the biases of convolution layers in both Generator and Discriminator are set to zero before updating. I am wondering if you can...

forward() error when use it inside a network as nn.Module

1

**The code is quite simple:** require 'caffe' model = nn.Sequential() model:add(caffe.Net('caffenet_deploy.prototxt', 'bvlc_reference_caffenet.caffemodel', 'test')) model:add(nn.Linear(1000,1)) input = torch.FloatTensor(10,3,227,227) output = model:forward(input) **But when I execute it, error occurs:** /home/vim/torch/install/bin/luajit: /home/vim/torch/install/share/lua/5.1/nn/Container.lua:67: In...