๐ป Code for Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection
-
Authors: Shoubin Yu, Zhongyin Zhao, Hao-shu Fang, Andong Deng, Haisheng Su, Dongliang Wang, Weihao Gan, Cewu Lu, and Wei Wu
-
Paper (IEEE Transactions on Circuits and Systems for Video Technology 2023)
We extract poses in ShanghaiTech in the same way as GEPC. As for Corridor, we adopt the same methods mentioned here. Once poses have been downloaded or extracted, change the data path in src/datasets/dataset_path.py to train or test models.
For ShanghaiTech
python train_test.py --exp_name ShanghaiTech_AlphaPose_train --dataset ShanghaiTech_AlphaPose
For Corridor
python train_test.py --exp_name Corridor_train --dataset Corridor
For ShanghaiTech
python train_test.py --exp_name ShanghaiTech_AlphaPose_test --dataset ShanghaiTech_AlphaPose --inference True --model_path your_path_to_model
For Corridor
python train_test.py --exp_name Corridor_test --dataset Corridor --inference True --model_path your_path_to_model