Yunfeng Diao is an assistant professor at the School of Computer Science, Hefei University of Technology, China. He received his Ph.D. from SWJTU, China. Previously he was a visiting Ph.D. student (mentored by Dr.He Wang) at the School of Computing, University of Leeds, UK and a research intern in Baidu Research, China. His current research interests include computer vision and security of machine learning.  

Review Service

Journals

International Journal of Computer Vision (IJCV), IEEE Transactions on Information Forensics and Security(TIFS), Transactions on Image Processing(TIP), IEEE Transactions on Multimedia(TMM), IEEE Transactions on Neural Networks and Learning Systems(TNNLS), Frontiers of Computer Science，Neurocomputing, Computer Vision and Image Understanding, Journal of Visual Communication and Image Representation, and The Visual Computer， 信息网络安全

Conferences

AAAI conference on Aritificial Intelligence (AAAI), European Conference on Computer Vision (ECCV), ACM International Conference on Multimedia (ACM MM), Computer Animation and Social Agents(CASA),Computer Graphics International(CGI) and Conference on Computational Visual Media (CVM)

Recent Publications

[8] He Wang^#, Yunfeng Diao^#.  Defending Black-box Classifiers by Bayesian Boundary Correction.   arxiv. 2023 

[7] Jiang Wan^#, Yunfeng Diao*^#, He Wang, Jianxin Sun, Meng Wang and Richang Hong, Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples, ACM Multimedia, 2023. 

[6] Yunfeng Diao, Tianjia Shao, Yongliang Yang, Kun Zhou and He Wang, BASAR:Black-box Attack on Skeletal Action Recognition,  In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  2021: 7597-7607. 

[5] He Wang^#, Yunfeng Diao^#, Zichang Tan and Guodong Guo, Defending Black-box Skeleton-based Human Activity Classifiers, the AAAI conference on Aritificial Intelligence (AAAI) 2023. 

[4] Yunfeng Diao^#, He Wang^#, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg, Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack, arxiv 2022.

[3] Yunfeng Diao, Xin Tang, He Wang, Emma Taylor, Shirui Xiao, Mengtian Xie and Wenming Cheng. A large-scale container dataset and a baseline method for container hole localization. Journal of Real-Time Image Processing (RTIP), 2022,19(3):577-589. 

[2]Yulin Zhang, Bo Ma, Longyao Liu, Xin Yi, Yunfeng Diao. "Self-paced uncertainty estimation for one-shot person re-identification." Applied Intelligence (2022): 1-15.

[1] Yunfeng Diao, Wenming Cheng, Run Du, Yaqing Wang and Jun Zhang. Vision-based detection of container lock holes using a modified local sliding window method. EURASIP Journal on Image and Video Processing, 2019, 69: 1-8.