This repo contains the Pytorch implementation of our paper:

Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning

Please download the extracted I3d features for ShanghaiTech dataset from these two links:

train i3d onedirve

test i3d onedrive

Extracted I3d features for Ucf-Crime:

train i3d onedirve

test i3d onedrive

checkpoint for Ucf-crime

The following files need to be adapted in order to run the code on your own machine:

• Change the file paths to the download datasets above in list/shanghai-i3d-test-10crop.list and list/shanghai-i3d-train-10crop.list for ShanghaiTech, or list/ucf-i3d.list and list/ucf-i3d-test.list for Ucf-Crime.
• Feel free to change the hyperparameters in option.py

After the setup, simply run the following command:

python main.py