X
Xianxu Hou
Researcher at Shenzhen University
Publications - 55
Citations - 966
Xianxu Hou is an academic researcher from Shenzhen University. The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 10, co-authored 45 publications receiving 538 citations. Previous affiliations of Xianxu Hou include The University of Nottingham Ningbo China.
Papers
More filters
Proceedings ArticleDOI
Deep Feature Consistent Variational Autoencoder
TL;DR: Zhang et al. as discussed by the authors employ a pre-trained deep convolutional neural network (CNN) and use its hidden features to define a feature perceptual loss for VAE training.
Posted Content
Deep Feature Consistent Variational Autoencoder
TL;DR: This work employs a pre-trained deep convolutional neural network and uses its hidden features to define a feature perceptual loss for VAE training, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality.
Journal ArticleDOI
End-to-End Single Image Fog Removal Using Enhanced Cycle Consistent Adversarial Networks
TL;DR: This work has developed an end-to-end learning system that uses unpaired fog and fogfree training images, adversarial discriminators and cycle consistency losses to automatically construct a fog removal system and contributes the first real world nature fog-fogfree image dataset for defogging research.
Journal ArticleDOI
Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
TL;DR: A generative adversarial training mechanism to force the variational autoencoder (VAE) to output realistic and natural images and a multi-view feature extraction strategy to extract effective image representations which can be used to achieve state of the art performance in facial attribute prediction.
Journal ArticleDOI
Urban Traffic Density Estimation Based on Ultrahigh-Resolution UAV Video and Deep Neural Network
TL;DR: It is shown that the enhanced single shot multibox detector (Enhanced-SSD) outperforms other DNN-based techniques and that deep learning techniques are more effective than traditional computer vision techniques in traffic video analysis.