This is the code for the paper
Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification,
Ali Diba*,
Mohsen Fayyaz*,
Vivek Sharma,
Amir Hossein Karami,
Mohammad Mahdi Arzani,
Rahman Yousefzadeh,
Luc Van Gool
(* equal contribution)
In this work we have introduced the new 3D convolutional neural network architectures for video classification named DenseNet3D and T3D.
If you find this code useful in your research, please cite:
@ARTICLE{2017arXiv171108200D,
author = {{Diba}, A. and {Fayyaz}, M. and {Sharma}, V. and {Karami}, A.~H. and
{Mahdi Arzani}, M. and {Yousefzadeh}, R. and {Van Gool}, L.},
title = "{Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification}",
journal = {ArXiv e-prints},
archivePrefix = "arXiv",
eprint = {1711.08200},
primaryClass = "cs.CV",
keywords = {Computer Science - Computer Vision and Pattern Recognition},
year = 2017,
month = nov,
adsurl = {http://adsabs.harvard.edu/abs/2017arXiv171108200D},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}