DisMouse: Disentangling Information from Mouse Movement Data

Guanhua Zhang, Zhiming Hu, Andreas Bulling
ACM UIST 2024, Pittsburgh, USA
[Project] [Paper]

Virtual environment setup

We recommend to setup a virtual environment using Anaconda.

Create a conda environment and install dependencies

conda env create --name dismouse --file=environment.yaml
conda activate dismouse

Clone our repository to download our code
```
git clone this_repo.git
```

Run the code to train DisMouse

Our code supports training using GPUs. You can also assign a particular card via CUDA_VISIBLE_DEVICES (e.g., the following commands use GPU card no.3). Simply execute

CUDA_VISIBLE_DEVICES=3 python main.py

Use your own configurations

Change parameters in templates.py -> mouse_autoenc and config.py -> TrainConfig

Train on your mouse dataset

Plug in your data loader function in dataset.py -> loadDataset (line 6)

Citation

If you find our code useful or use it in your own projects, please cite our paper:

@inproceedings{zhang24_uist,
  title = {DisMouse: Disentangling Information from Mouse Movement Data},
  author = {Zhang, Guanhua and Hu, Zhiming and Bulling, Andreas},
  year = {2024},
  pages = {1--13},
  booktitle = {Proc. ACM Symposium on User Interface Software and Technology (UIST)},
  doi = {10.1145/3654777.3676411}
}

Acknowledgements

Our work is built on the codebase of Diffusion Autoencoders. Thanks to the authors for sharing their code.

2 KiB Raw Blame History