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 (Best Award), and the journal paper "Glitch in the Matrix!": A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization submitted to CVIU.

LAV-DF Dataset

Download

To use this LAV-DF dataset, you should agree the terms and conditions.

Download link: Google Drive, or HuggingFace.

License

This project is under the CC BY-NC 4.0 license. See LICENSE for details.

References

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

The conference paper,

@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,

@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