SPAct

KO | EN

gitlite — search

#python #react #ai #machine-learning #docker #nodejs #awesome #cli #kubernetes #awesome-list #pytorch #security #mcp #open-source

(★ 21)

Official code repository for SPAct: Self-supervised Privacy Preservation for Action Recognition [CVPR-2022]

SPAct Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# SPAct
Official code repository for SPAct: Self-supervised Privacy Preservation for Action Recognition [CVPR-2022]

### Dataset preparation

UCF101: https://www.crcv.ucf.edu/data/UCF101/UCF101.rar
 HMDB51: http://serre-lab.clps.brown.edu/wp-content/uploads/2013/10/hmdb51_org.rar
 VISPR: https://tribhuvanesh.github.io/vpa/
 PA-HMDB51: https://github.com/TAMU-VITA/PA-HMDB51
 LSHVU dataset: https://github.com/holistic-video-understanding/HVU-Dataset

### Intialization of networks
``cd initialization`` 
To run initialization training for anonymization function ($f_A$): 
```
 python train_recon.py --run_id="give_any_expname_you_like"
 # add --restart argument to continue the stopped training
 ```

### Training of Anonymization function
``cd anonymization_training`` 
Load the initilization weights of $f_A$, $f_B$ and $f_T$ and start training with the following command:
```
 python train_ssl_minimax2.py --run_id="give_any_expname_you_like"
```

### Evaluation of learned anonymization function
TODO: Add code

### Anonymization Visualization
TODO: Add code

### Citation

If you find the repo useful for your research, please consider citing our paper: 
```
@inproceedings{spact,
  title={SPAct: Self-supervised Privacy Preservation for Action Recognition},
  author={Dave, Ishan Rajendrakumar and Chen, Chen and Shah, Mubarak},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2022}
}
```
### Useful code repositories

[1] Privacy preserving action recognition (Wu et al., TPAMI 2020): https://github.com/VITA-Group/Privacy-AdversarialLearning 
 [2] PA-HMDB annoatations https://github.com/VITA-Group/PA-HMDB51
 [3] PyTorch Implementation of UNet: https://github.com/milesial/Pytorch-UNet
 [4] Torchvision models: https://github.com/pytorch/vision/tree/main/torchvision/models

SPAct

SPAct Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

SPAct

SPAct Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README