Skip to content
Actionness Estimation Using Hybrid Fully Convolutional Networks
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
example add demo code Jul 29, 2016
proto add demo code Jul 29, 2016
README.md
VGG_mean.mat add demo code Jul 29, 2016
demo_a_fcn.m add demo code Jul 29, 2016
demo_m_fcn.m Update demo_m_fcn.m Jul 29, 2016
example.avi add demo code Jul 29, 2016

README.md

Actionness Estimation Using Hybrid FCNs

Here we provide the code of actionness estimation with hybrid fully convolutional networks from the following paper:

Actionness Estimation Using Hybrid Fully Convolutional Netoworks
Limin Wang, Yu Qiao, Xiaou Tang, and Luc Van Gool, in CVPR, 2016

Updates

  • Jul 22, 2016
    • Initilaize repo of actionness estimation.

Demo code

  • demo_a_fcn.m: an example showing actionness estimation with A-FCN.
  • demo_m_fcn.m: an example showing actionness estimation with M-FCN.
  • For optical flow extraction, we use TVL1 Optical Flow
    You need download our dense flow code and compile it by yourself. Dense Flow

Download

Questions

Contact

You can’t perform that action at this time.