X
Xiaofei Zhou
Researcher at Hangzhou Dianzi University
Publications - 49
Citations - 643
Xiaofei Zhou is an academic researcher from Hangzhou Dianzi University. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 9, co-authored 30 publications receiving 256 citations. Previous affiliations of Xiaofei Zhou include Shanghai University & University of Technology, Sydney.
Papers
More filters
Journal ArticleDOI
Rapid and robust two-dimensional phase unwrapping via deep learning.
Teng Zhang,Shaowei Jiang,Zixin Zhao,Krishna Dixit,Xiaofei Zhou,Jia Hou,Yongbing Zhang,Chenggang Yan +7 more
TL;DR: A deep convolutional neural network (DCNN) based method to perform rapid and robust two-dimensional phase unwrapping, with noise suppression and strong feature representation capabilities, which out-performed the conventional phase unwrap algorithms.
Journal ArticleDOI
Improving Video Saliency Detection via Localized Estimation and Spatiotemporal Refinement
TL;DR: The experimental results demonstrate that the proposed framework is able to consistently and significantly improve the saliency detection performance of various video saliency models, thereby achieving the state-of-the-art performance.
Journal ArticleDOI
Dynamic Selective Network for RGB-D Salient Object Detection
Wen Hongfa,Chenggang Yan,Xiaofei Zhou,Runmin Cong,Yaoqi Sun,Bolun Zheng,Jiyong Zhang,Yongjun Bao,Guiguang Ding +8 more
TL;DR: Zhang et al. as mentioned in this paper proposed a dynamic selective network (DSNet) to perform salient object detection (SOD) in RGB-D images by taking full advantage of the complementarity between the two modalities.
Journal ArticleDOI
Improving Saliency Detection Via Multiple Kernel Boosting and Adaptive Fusion
TL;DR: A novel framework to improve the saliency detection performance of an existing saliency model, which is used to generate the initial saliency map, and an adaptive fusion method via learning a quality prediction model for saliency maps to effectively fuse the initialsaliency map with the complementarySaliency map.
Journal ArticleDOI
Edge-Aware Multiscale Feature Integration Network for Salient Object Detection in Optical Remote Sensing Images
TL;DR: An edge-aware multiscale feature integration network (EMFI-Net) is proposed for salient object detection by conducting multiscales feature integration under the explicit and implicit assistance of salient edge cues to introduce the edge information to precisely detect salient objects in RSIs.