no code implementations • 18 Jul 2023 • Lin Yuan, Kai Liang, Xiao Pu, Yan Zhang, Jiaxu Leng, Tao Wu, Nannan Wang, Xinbo Gao
This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework.
1 code implementation • 24 Aug 2022 • Kai Liang, Jun Wang, Abhir Bhalerao
Previous works often adopt physical variables such as driving speed, acceleration and so forth for lane change classification.
no code implementations • 20 Nov 2021 • Constantinos Psomas, Minglei You, Kai Liang, Gan Zheng, Ioannis Krikidis
In this paper, we provide a complete framework for the design and analysis of far-field SWIPT under safety constraints.
no code implementations • 16 Nov 2021 • Kai Liang, Huiru Zhong, Haoning Chen, Youlong Wu
Due to limited communication resources at the client and a massive number of model parameters, large-scale distributed learning tasks suffer from communication bottleneck.
no code implementations • 4 Feb 2021 • Kai Liang, Youlong Wu
We propose a practical and efficient estimator based on an r-bit Wynzer-Ziv estimator proposed by Mayekar et al., which requires no probabilistic assumption on the data.
Information Theory Information Theory