Official repository for TikTok-DeepFake (TT-DF). TikTok-DeepFake (TT-DF) is a pioneering large-scale diffusion-based dataset containing 6,120 forged videos with 1,378,857 synthetic frames, specifically tailored for human body forgery detection.
Wenkui Yang, Zhida Zhang, Xiaoqiang Zhou, Junxian Duan, Jie Cao
Thank you for your incredible support and interest in our project! TT-DF dataset is now available via Google Drive!
If you find any problems, please contact us via - wenkui.yang@cripac.ia.ac.cn
@inproceedings{yang2024tt,
title={TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery Detection},
author={Yang, Wenkui and Zhang, Zhida and Zhou, Xiaoqiang and Duan, Junxian and Cao, Jie},
booktitle={Chinese Conference on Pattern Recognition and Computer Vision (PRCV)},
pages={429--443},
year={2024},
organization={Springer}
}