Thank you for your great help!
I have another question. About THUMOS14, may I ask what is the way you take to extract features?
The FC layer output of anet is 200 classes. Did you modify the FC layer and then train on THUMOS14?
Hi @coder-LeeTao , we did not finetune this network on THUMOS14. We direct use the output of last fc layer (without softmax) as the feature. Actually, you can also use the 2048-dim fc layer.
Thank you for your great help! I have another question. About THUMOS14, may I ask what is the way you take to extract features? The FC layer output of anet is 200 classes. Did you modify the FC layer and then train on THUMOS14?