YanZhang-bit

"x = torch.sigmoid(0.01*self.conv3(x))" why multi 0.01 before sigmoid function?

Could I share your extracted features for THUMOS 2014?

2

Hi @piergiaj Thanks for sharing your code!I have repeat your THUMOS'14 experiments in your paper "Temporal gaussian mixture layer for videos"(Table 6),but i can't achieve the performance mentioned in your...