1. paper
(1) this paper
Simonyan K, Zisserman A. Two-Stream Convolutional Networks for Action Recognition in Videos[J]. Computational Linguistics, 2014, 1(4):568-576.
http://xueshu.baidu.com/s?wd=paperuri%3A%28de9c108a5e08f4f502cd6bce30e5ce9f%29&filter=sc_long_sign&tn=SE_xueshusource_2kduw22v&sc_vurl=http%3A%2F%2Fde.arxiv.org%2Fpdf%2F1406.2199&ie=utf-8&sc_us=10825451380853652474
(2) action recognition overview
https://github.com/jinwchoi/awesome-action-recognition
A curated list of action recognition and related area (e.g. object recognition, pose estimation) resources, inspired by awesome-computer-vision.
2. code
https://github.com/jeffreyhuang1/two-stream-action-recognition
based on pytorch
3. install Anaconda and Pytorch
(1)Anaconda
conda info --envs
(2) Pytorch
pytorch 安装过程的步骤:
https://ptorch.com/news/37.html
使用conda安装指定版本
# 比如我们安装 v0.1.10
conda install pytorch=0.1.10 -c soumith
4. git clone two-stream-action-recognition
git clone https://github.com/jeffreyhuang1/two-stream-action-recognition
but can not download mode file from google, 555