no code implementations • 30 Jul 2019 • Jia-xin Cai, Hongfeng Zhu
The generative adversarial networks was employed to translate the original lung image to the segmented image.
no code implementations • 2 Aug 2018 • Jia-xin Cai, Xin Tang
Action recognition has attracted increasing attention from RGB input in computer vision partially due to potential applications on somatic simulation and statistics of sport such as virtual tennis game and tennis techniques and tactics analysis by video.
no code implementations • 13 Mar 2016 • Jia-xin Cai, Xin Tang, Lifang Zhang, Guocan Feng
In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected discriminative frames and the second-phase dictionary is built for recognition using reconstruction errors of the first-phase dictionary as input features.