314-learning-normal-dynamics-in-videos-with-meta-prototype-network
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.6%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: SZU-AdvTech-2023
- Language: Python
- Default Branch: main
- Size: 675 MB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Codes_MPN
Official codes of CVPR21 paper: Learning Normal Dynamics in Videos with Meta Prototype Network (https://arxiv.org/abs/2104.06689)
MPN Framework
Paper Results on Unsupervised VAD
Paper Results on Few-shot VAD
Preparation
Please download the corresponding benchmarks in 'data' directory. Then prepare the environment as in requirement.txt. We have uploaded several trained models on online (Baidunetdisk(linkhttps://pan.baidu.com/s/1qcGmdmZlmAgqsAzwi5BhA codemapz) or Drive (https://drive.google.com/drive/folders/1ketomxctszHo7jpGQS3RxbZGq7eM3e4?usp=sharing)).
Unsupervised Anomaly Detection Model Training
Run 'python Train.py' to train a model with DPU model.
Unsupervised Anomaly Detection Model Testing
Run 'python Test.py' to train a model with DPU model.
Meta-learning Anomaly Detection Model Training
Run 'python Train_meta.py' to train a model with MPU model.
Meta-learning Anomaly Detection Model Testing
Run 'python Test_meta.py' to test a model with MPU model.
If you find this work helpful, please cite:
@inproceedings{Lv2021MPN,
author = {Hui LV and
Chen Chen and
Zhen Cui and
Chunyan Xu and
Yong Li and
Jian Yang},
title = {Learning Normal Dynamics in Videos with Meta Prototype Network},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021}
}
Owner
- Name: SZU-AdvTech-2023
- Login: SZU-AdvTech-2023
- Kind: organization
- Repositories: 1
- Profile: https://github.com/SZU-AdvTech-2023