Hidden-Two-Stream
Hidden-Two-Stream copied to clipboard
bryanyzhu
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Hi, Thanks for sharing your work. I am wondering how do you load the 11 frames for MotionNet training? For each video clip, do you take one set of 11...
That was great job. Can the **MotionNet** be separately trained with ground truth optical flow images？
Hi, I am inspired much by your work, but confused about some details. In Table 4 of your paper, there are some experiments on THUMOS14. I'd like to know what...
