Daichi Zhang   Ph.D. Candidate University of Chinese Academy of Sciences Beijing, China, 100084 Bachelor Dept. of Computer Science and Technology Tsinghua University Beijing, China, 100084 Email: zhangdaichi20@mails.ucas.edu.cn Github: Daisy Zhang [Google Scholar]

Biography

I am a third-year PhD student in University of Chinese Academy of Sciences (2020-). Before that, I got my Bachelor degree in Dept. of Computer Science and Technology, Tsinghua University (2016-2020).

My research interests include deep learning, computer vision and AI security. Recently I am working on Face Forgery Detection.

Competitions

• Deepfake Detection Challenge (DFDC) 2020: Top twenty in the world rank, team with TSAIL Group, Tsinghua University.

Publications

• Deepfake Video Detection with Spatiotemporal Dropout Transformer
  Daichi Zhang, Fanzhao Lin, Yingying Hua, Pengju Wang, Dan Zeng, Shiming Ge
  Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022, Oral
  
• Detecting Deepfake Videos with Temporal Dropout 3DCNN
  Daichi Zhang, Chenyu Li, Fanzhao Lin, Dan Zeng, Shiming Ge
  Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021
  
• Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation
  Chenyu Li, Shiming Ge, Daichi Zhang, Jia Li
  Proceedings of the 28th ACM International Conference on Multimedia (ACM MM), 2020
  
• Deepfake Video Detection via Predictive Representation Learning
  Shiming Ge, Fanzhao Lin, Chenyu Li, Daichi Zhang, Weipeng Wang, Dan Zeng
  ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2022
  
• Interpret The Predictions Of Deep Networks Via Re-Label Distillation
  Yingying Hua, Shiming Ge, Daichi Zhang
  IEEE International Conference on Multimedia and Expo (ICME), 2021
  
• Interpretable Face Manipulation Detection via Feature Whitening
  Yingying Hua, Daichi Zhang, Pengju Wang, Shiming Ge
  International Conference on Machine Learning (ICML Workshop), 2021
  
• Research progress in the interpretability of deep learning models
  Yingying Hua, Daichi Zhang, Shiming Ge
  Journal of Cyber Security 5 (3), 1-12, 2020
  

Projects

• Awesome Deepfakes Detection
  Collection of Deepfakes Detection datasets, competitions, tools, papers and repos.
  
• Awesome Deepfakes
  Collection of Deepfakes datasets, tools, papers and repos.
  

Services

Conference reviewer:
ECCV 2022; AAAI 2021; CVPR 2021
2022 by Daichi Zhang