CT-Net: Channel Tensorization Network for Video Classification

CT-Net

CT-Net: Channel Tensorization Network for Video Classification

@inproceedings{
li2021ctnet,
title={{{}CT{}}-Net: Channel Tensorization Network for Video Classification},
author={Kunchang Li and Xianhang Li and Yali Wang and Jun Wang and Yu Qiao},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=UoaQUQREMOs}
}

Overview

[2021/6/3] We release the PyTorch code of CT-Net. More details and models will be available.

Model Zoo

More models will be released in a month…

Now we release the model for visualization, please download it from here and put it in ./model. (passward: t3to)

Install

pip install -r requirements.txt

Dataset

In our paper, we conduct experiments on Kinetics-400, Something-Something V1&V2, UCF101, and HMDB51. Please refer to TSM repo for the detailed guide of data pre-processing.

Training and Testing

 

 

 

To finish reading, please visit source site