Anqi111/MDPE_Dataset

---
language:
- zh
license: cc-by-nc-sa-4.0
size_categories:
- 100B<n<1T
task_categories:
- video-classification
---

# MDPE Dataset
MDPE is a multimodal deception dataset. Besides deception features, it also includes individual differences information in personality and emotional expression characteristics. MDPE not only supports deception detection, but also provides conditions for tasks such as personality recognition and emotion recognition, and can even study the relationships between them.

[Github Repo](https://github.com/cai-cong/MDPE)

# News
* 2025.12.17: Fixed labels files and some file naming errors. We strongly recommend that users who downloaded the dataset prior to [December 17, 2025] download the latest version of the labels file.
* 2025.09.26: We have released an updated version of this dataset.

## Dataset Download

The data are passcode protected. Please download and send the signed [EULA](https://drive.google.com/file/d/1A1F8szMOTf9-rK8DYD23GruBArtnYdLl/view?usp=sharing) to [[e-mail]]([e-mail]) for access request.

## Citation
For more details about MDPE, please refer to:
[MDPE: A Multimodal Deception Dataset with Personality and Emotional Characteristics](https://arxiv.org/abs/2407.12274)

Please cite our paper if you find our work useful for your research:

```
@inproceedings{cai2025mdpe,
title={Mdpe: A multimodal deception dataset with personality and emotional characteristics},
author={Cai, Cong and Liang, Shan and Liu, Xuefei and Zhu, Kang and Wen, Zhengqi and Tao, Jianhua and Xie, Heng and Cui, Jizhou and Ma, Yiming and Cheng, Zhenhua and others},
booktitle={Proceedings of the 33rd ACM International Conference on Multimedia},
pages={12957--12964},
year={2025}
}
```