Yongyi Tang

Results 2 issues of Yongyi Tang

Hi, I would like to directly extract feature from the pretrain nets. How can I modify the code since cnn_ucf101_fusion.m is supposed to train the nets.

Hi, I would like to know how to preprocess the kinetics-400 for reproducing the results. I found that extracting tvl1 flow before rescale the rgb images leads to worse flow...