no code implementations • 15 Feb 2023 • Navin Cooray, Zhenglin Li, Jinzhuo Wang, Christine Lo, Mahnaz Arvaneh, Mkael Symmonds, Michele Hu, Maarten De Vos, Lyudmila S Mihaylova
This study proposes a framework for automated limb-movement detection by fusing data from two EMG sensors (from the left and right limb) through a Dirichlet process mixture model.
no code implementations • ICML 2020 • Ying Huang, Shangfeng Qiu, Wenwei Zhang, Xianghui Luo, Jinzhuo Wang
Researches using margin based comparison loss demonstrate the effectiveness of penalizing the distance between face feature and their corresponding class centers.
no code implementations • 20 Jan 2020 • Ying Huang, Wenwei Zhang, Jinzhuo Wang
Face anti-spoofing is crucial for the security of face recognition system, by avoiding invaded with presentation attack.
1 code implementation • 13 Jun 2017 • Baoyang Chen, Wenmin Wang, Jinzhuo Wang, Xiongtao Chen
To overcome those problems, we propose a new framework that produce imaginary videos by transformation generation.
no code implementations • 13 Jun 2017 • Xiongtao Chen, Wenmin Wang, Jinzhuo Wang, Weimian Li, Baoyang Chen
In this paper, we present a novel deep architecture called bidirectional predictive network (BiPN) that predicts intermediate frames from two opposite directions.
no code implementations • 13 Jun 2017 • Jinzhuo Wang, Wenmin Wang, Ronggang Wang, Wen Gao
We show such setting can preserve more contexts of local features and its evolutions which are beneficial for move prediction.
no code implementations • NeurIPS 2016 • Jinzhuo Wang, Wenmin Wang, Xiongtao Chen, Ronggang Wang, Wen Gao
This paper instead explores contexts as early as possible and leverages their evolutions for action recognition.