Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Christoph Feichtenhofer a098f0828d | 7 years ago | |
---|---|---|
MexConv3D @ 2b58a8fd21 | 7 years ago | |
hmdb51_splits | 7 years ago | |
matconvnet | 7 years ago | |
network_surgery | 7 years ago | |
ucf101_splits | 7 years ago | |
.gitmodules | 7 years ago | |
LICENSE | 7 years ago | |
README.md | 7 years ago | |
cnn_setup_environment.m | 7 years ago | |
cnn_train_dag.m | 7 years ago | |
cnn_ucf101_fusion.m | 7 years ago | |
cnn_ucf101_get_flow_batch.m | 7 years ago | |
cnn_ucf101_get_frame_batch.m | 7 years ago | |
cnn_ucf101_get_im_flow_batch.m | 7 years ago | |
cnn_ucf101_setup_data.m | 7 years ago | |
cnn_ucf101_spatial.m | 7 years ago | |
cnn_ucf101_temporal.m | 7 years ago | |
compile.m | 7 years ago | |
getBatchWrapper_ucf101_flow.m | 7 years ago | |
getBatchWrapper_ucf101_imgs.m | 7 years ago | |
getBatchWrapper_ucf101_rgbflow.m | 7 years ago |
================================================================================
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 questions regarding the implementation please contact:
Christoph Feichtenhofer <feichtenhofer AT tugraz.at>
================================================================================
Download the code git clone --recursive https://github.com/feichtenhofer/twostreamfusion
Compile the code by running compile.m
.
Edit the file cnn_setup_environment.m to adjust the models and data paths.
Download pretrained model files and the datasets, linked below and unpack them into your models/data directory.
cnn_ucf101_spatial();
to train the appearance network stream.cnn_ucf101_temporal();
to train the optical flow network stream.cnn_ucf101_fusion();
this will use the downloaded models and demonstrate training of our final architecture on UCF101/HMDB51.
opts.train.gpus
cudnnWorkspaceLimit
(512MB is default)Pre-computed optical flow images and resized rgb frames for the UCF101 and HMDB51 datasets
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》