About context-gated-convolution for action recgnition

[zzwei1]

Nice work! I wonna use context-gated-convolution in action recgnition. I noticed that you use torch.nn.Unfold in layer.py, and it needs a 4-D input(batch x channel x height x width). But I don't know how to do to extend context-gated-convolution to a 5-D input (batch x channel x frams x height x width) . Will you release your code for action recgnition in the paper? Thanks!

[XudongLinthu]

Thanks for the interest! Plan to release action recognition codes in the coming month. One note is that we didn't have experiments of CGC+3D convolution. We reported CGC+ (2+1)D, where tensors can be always transformed to less than 5 dimensions.