[project page] [paper]

If you find this work helpful for your research, please cite our following paper:

D. Tran, H. Wang, L. Torresani, J. Ray, Y. LeCun and M. Paluri. A Closer Look at Spatiotemporal Convolutions for Action Recognition. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

@inproceedings{r2plus1d_cvpr18,
    title = {A Closer Look at Spatiotemporal Convolutions for Action Recognition},
    author = {Du Tran and Heng Wang and Lorenzo Torresani and Jamie Ray and Yann LeCun and
               Manohar Paluri},
    booktitle = {CVPR},
    year = 2018
}

If you have any question or feedback about the code, please contact: [email protected], [email protected].

R2Plus1D requires the following dependencies:

• Caffe2 and its dependencies.
• OpenCV (tested on 3.4.1) and ffmpeg.
• And lmdb, python-lmdb, and pandas.

• You need to install ffmpeg, OpenCV, and caffe2. Caffe2 installation instructions can be found here. You also need to install lmdb, python-lmdb, and pandas.

We provide some basic tutorials for you to get familar with the code and tools.

• Installation Guide
• Training Kinetics from scratch
• Finetuning R(2+1)D on HMDB51
• Dense prediction
• Feature extraction
• Download and evaluate pre-trained models

R2Plus1D is Apache 2.0 licensed, as found in the LICENSE file.

The authors would like to thank Ahmed Taei, Aarti Basant, Aapo Kyrola, and the Facebook Caffe2 team for their help in implementing ND-convolution, in optimizing video I/O, and in providing support for distributed training. We are grateful to Joao Carreira for sharing I3D results on the Kinetics validation set.