README.md

---
language:
- en
tags:
- deepfakes
- video
pretty_name: LAV-DF
task_categories:
- video-classification
paperswithcode_id: lav-df
license: cc
size_categories:
- 100K<n<1M
extra_gated_heading: Access LAV-DF dataset on Hugging Face
extra_gated_prompt: To use this LAV-DF dataset, you should agree the [terms and conditions](https://github.com/ControlNet/LAV-DF/blob/master/TERMS_AND_CONDITIONS.md).
---
# Localized Audio Visual DeepFake Dataset (LAV-DF)

This repo is the dataset for the DICTA paper [Do You Really Mean That? Content Driven Audio-Visual 
Deepfake Dataset and Multimodal Method for Temporal Forgery Localization](https://ieeexplore.ieee.org/document/10034605)
(Best Award), and the journal paper ["Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual 
Forgery Detection and Localization](https://arxiv.org/abs/2305.01979) submitted to CVIU.

## LAV-DF Dataset

### Download

To use this LAV-DF dataset, you should agree the [terms and conditions](https://github.com/ControlNet/LAV-DF/blob/master/TERMS_AND_CONDITIONS.md).

Download link: [Google Drive](https://drive.google.com/file/d/1-OQ-NDtdEyqHNLaZU1Lt9Upk5wVqfYJw/view?usp=sharing), or [HuggingFace](https://huggingface.co/datasets/ControlNet/LAV-DF).

## License

This project is under the CC BY-NC 4.0 license. See [LICENSE](https://github.com/ControlNet/LAV-DF/blob/master/LICENSE) for details.

## References

If you find this work useful in your research, please cite them.

The conference paper,
```bibtex
@inproceedings{cai2022you,
  title = {Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization},
  author = {Cai, Zhixi and Stefanov, Kalin and Dhall, Abhinav and Hayat, Munawar},
  booktitle = {2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA)},
  year = {2022},
  doi = {10.1109/DICTA56598.2022.10034605},
  pages = {1--10},
  address = {Sydney, Australia},
}
```

The extended journal version currently under review at CVIU,
```bibtex
@article{cai2023glitch,
  title = {Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization},
  author = {Cai, Zhixi and Ghosh, Shreya and Dhall, Abhinav and Gedeon, Tom and Stefanov, Kalin and Hayat, Munawar},
  journal = {arXiv preprint arXiv:2305.01979},
  year = {2023},
}
```

The arxiv version available for the conference paper: https://arxiv.org/abs/2204.06228
The arxiv version available for the journal paper: https://arxiv.org/abs/2305.01979