no code implementations • 19 Mar 2020 • Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, Jie Yang
In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules.
no code implementations • 23 Feb 2020 • Zihao Wang, Enmei Tu, Zhou Meng
The quality of a graph is determined jointly by three key factors of the graph: nodes, edges and similarity measure (or edge weights), and is very crucial to the success of graph-based semi-supervised learning (SSL) approaches.
no code implementations • 2 Jan 2020 • Enmei Tu, Guanghao Zhang, Shangbo Mao, Lily Rachmawati, Guang-Bin Huang
The prosperity of artificial intelligence has aroused intensive interests in intelligent/autonomous navigation, in which path prediction is a key functionality for decision supports, e. g. route planning, collision warning, and traffic regulation.
no code implementations • 19 Dec 2019 • Xiao Han, ZiHao Wang, Enmei Tu, Gunnam Suryanarayana, Jie Yang
Deep learning demands a huge amount of well-labeled data to train the network parameters.
no code implementations • 28 May 2019 • Enmei Tu, Jie Yang
Semi-supervised learning, which has emerged from the beginning of this century, is a new type of learning method between traditional supervised learning and unsupervised learning.
no code implementations • 30 Oct 2016 • Enmei Tu, Guanghao Zhang, Lily Rachmawati, Eshan Rajabally, Guang-Bin Huang
A biological neural network is constituted by numerous subnetworks and modules with different functionalities.
no code implementations • 3 Jun 2016 • Enmei Tu, Yaqian Zhang, Lin Zhu, Jie Yang, Nikola Kasabov
In this paper, we propose a new graph-based $k$NN algorithm which can effectively handle both Gaussian distributed data and nonlinear manifold distributed data.
no code implementations • 17 Mar 2016 • Enmei Tu, Nikola Kasabov, Jie Yang
This paper proposes a new method for an optimized mapping of temporal variables, describing a temporal stream data, into the recently proposed NeuCube spiking neural network architecture.