================================================================================

This repository contains the code for our CVPR 2016 paper:

Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman
"Convolutional Two-Stream Network Fusion for Video Action Recognition"
in Proc. CVPR 2016

If you find the code useful for your research, please cite our paper:

    @inproceedings{feichtenhofer2016convolutional,
      title={Convolutional Two-Stream Network Fusion for Video Action Recognition},
      author={Feichtenhofer, Christoph and Pinz, Axel and Zisserman, Andrew},
      booktitle={Conference on Computer Vision and Pattern Recognition (CVPR)},
      year={2016}
    }

The code was tested on Ubuntu 14.04 and Windows 10 using MATLAB R2015b and NVIDIA Titan X or Z GPUs.

If you have any question regarding the implementation please contact:

Christoph Feichtenhofer <feichtenhofer AT tugraz.at>

================================================================================

1. Download the code git clone --recursive https://github.com/feichtenhofer/twostreamfusion

2. Compile the code by running compile.m.

• This will also compile a modified (and older) version of the MatConvNet toolbox. In case of any issues, please follow the installation instructions on the MatConvNet homepage.

3. Download pretrained model files and the datasets, linked below and unpack them into your models/data directory.

4. Edit the file cnn_setup_environment.m to adjust the models and data paths.

5. Run cnn_ucf101_fusion(); this will use the downloaded models and demonstrate training of our final architecture on UCF101.

• In case you would like to train on the CPU, clear the variable opts.train.gpus
• In case you encounter memory issues on your GPU, consider decreasing the cudnnWorkspaceLimit (512MB is default)

• Spatial network for UCF101 (split1)
• Temporal network for UCF101 (split1)

Pre-computed optical flow images and resized rgb frames for the UCF101 and HMDB51 datasets

• UCF101 RGB: part1 part2 part3

• UCF101 Flow: part1 part2 [part3](<https://onedrive.live.com/download?cid=33A1ED4EC8B18772&resid=33A1ED4EC8B18772%2168909&authkey=AAUtcU2BYW1_ghk)

• Our Optical flow extraction tool provides OpenCV wrappers for optical flow extraction on a GPU.