About experiments on ActivityNet1.3

[blowing-wind]

Hi, thanks for your excellent and inspiring work. The anchor-based part got a promising result on on thumos14 dataset. However, when I tried it on anet dataset, only got a average map of about 13, which is much lower than the result reported on paper. So I wonder if you adpoted the same network architecture in anet as in thumos14, looking forward to your reply, thanks.