J
Junyu Dong
Researcher at Ocean University of China
Publications - 484
Citations - 6570
Junyu Dong is an academic researcher from Ocean University of China. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 30, co-authored 399 publications receiving 3553 citations. Previous affiliations of Junyu Dong include Qingdao University.
Papers
More filters
Proceedings ArticleDOI
An Evaluation of Deep Learning in Loop Closure Detection for Visual SLAM
TL;DR: This paper performs a comparison and analysis of several popular deep neural networks and traditional methods for loop closure detection and concludes that deep neural network is suitable forloop closure detection.
Proceedings ArticleDOI
Deep hashing learning networks
TL;DR: This paper proposes a supervised hashing learning method based on a well designed deep convolutional neural network, which tries to learn hashing code and compact representations of data simultaneously.
Journal ArticleDOI
A dual-cue network for multispectral photometric stereo
TL;DR: A dual-cue fused network designed by designing two stacked deep network that is robust to non-Lambertian surfaces and complex illumination environments, such as ambient light and variant light directions, and outperforms existing methods.
Journal ArticleDOI
Associated Spatio-Temporal Capsule Network for Gait Recognition
TL;DR: An automated learning system, with an associated spatio-temporal capsule network (ASTCapsNet) trained on multi-sensor datasets, to analyze multimodal information for gait recognition and a Bayesian model is employed for the decision-making of class labels.
Journal ArticleDOI
Comprehensive assessment of non-uniform illumination for 3D heightmap reconstruction in outdoor environments
TL;DR: Three useful approaches are presented including an improved self-adaptive method, a FSAM (fast self- Adaptive method) and a manual correction method, to correct non-uniform illumination and eliminate the distortions for the reconstruction of 3D surface heightmaps.