1 code implementation • 10 Jan 2024 • Haonan Shi, Tu Ouyang, An Wang
The experiment results show that LDC-MIA can improve TPR at low FPR by up to 4x compared to the other difficulty calibration based MIAs.
no code implementations • 31 Jul 2023 • Wanshu Yu, Haonan Shi, Hongyun Xu
In order to provide sufficient privacy protection for users' trajectory datasets, this paper develops a study on trajectory privacy against re-identification attacks, proposing a trajectory K-anonymity model based on Point Density and Partition (KPDP).
1 code implementation • CVPR 2022 • Wenwen Pan, Haonan Shi, Zhou Zhao, Jieming Zhu, Xiuqiang He, Zhigeng Pan, Lianli Gao, Jun Yu, Fei Wu, Qi Tian
Audio-Guided video semantic segmentation is a challenging problem in visual analysis and editing, which automatically separates foreground objects from background in a video sequence according to the referring audio expressions.