Results reproducibility about action-recognition-visual-attention HOT 3 OPEN

HMDB-51 provides three train-test splits . We just used split 1. Hollywood2 also provides a train-test split. For validation we used 15% of the training data as validation set and the rest 85% for training. We noted the cost at best performance on the validation set. We then trained on the entire training data until the cost reached the same value as noted with the validation set separated.
Will share the txt files.

from action-recognition-visual-attention.

@kracwarlock Hi, also hope you can share your txt files, Thanks

from action-recognition-visual-attention.

I am trying to figure out how was the 1st attention initialized. In the attached figure, l1?

from action-recognition-visual-attention.