search

shuyueL / FFNet

Implementation of our CVPR 2018 Paper (FFNet: Video Fast-Forwarding via Reinforcement Learning)
GNU General Public License v3.0
20 stars 4 forks source link

Alexnet Architecture details #4

Closed niti1405 closed 3 years ago

niti1405 commented 5 years ago

I want to know the Alexnet architecture details that you have used to extract the features from video frames. As you have mentioned in the white paper - "Alexnet fc7 features (4096-dimensional) to represent each video frame and tune the parameters in each method to have the best performance."

What are the parameter that you have tuned/changed?

shuyueL commented 5 years ago

@niti1405 We did not tune Alexnet. We tuned the parameters in the compared methods so that they had the best performance they were able to get.