Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection

P An, Z Wang, C Zhang - Information Processing & Management, 2022 - Elsevier
Previous studies have adopted unsupervised machine learning with dimension reduction
functions for cyberattack detection, which are limited to performing robust anomaly detection …

V2v-posenet: Voxel-to-voxel prediction network for accurate 3d hand and human pose estimation from a single depth map

G Moon, JY Chang, KM Lee - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Most of the existing deep learning-based methods for 3D hand and human pose estimation
from a single depth map are based on a common framework that takes a 2D depth map and …

Deepprior++: Improving fast and accurate 3d hand pose estimation

M Oberweger, V Lepetit - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations
of a hand given a depth map. Since its publication early 2015, it has been outperformed by …

A2j: Anchor-to-joint regression network for 3d articulated pose estimation from a single depth image

F **ong, B Zhang, Y **ao, Z Cao, T Yu… - Proceedings of the …, 2019 - openaccess.thecvf.com
For 3D hand and body pose estimation task in depth image, a novel anchor-based approach
termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is …

Pose guided structured region ensemble network for cascaded hand pose estimation

X Chen, G Wang, H Guo, C Zhang - Neurocomputing, 2020 - Elsevier
Hand pose estimation from single depth images is an essential topic in computer vision and
human computer interaction. Despite recent advancements in this area promoted by …

Federated multidomain learning with graph ensemble autoencoder GMM for emotion recognition

C Zhang, M Li, D Wu - IEEE Transactions on Intelligent …, 2022 - ieeexplore.ieee.org
Facial expression cognition technology continues to face challenges from certain
perspectives despite the fact that there have been significant recent learning advances in …

A survey on 3D hand pose estimation: Cameras, methods, and datasets

R Li, Z Liu, J Tan - Pattern Recognition, 2019 - Elsevier
Abstract 3D Hand pose estimation has received an increasing amount of attention,
especially since consumer depth cameras came onto the market in 2010. Although …

Shpr-net: Deep semantic hand pose regression from point clouds

X Chen, G Wang, C Zhang, TK Kim, X Ji - IEEE Access, 2018 - ieeexplore.ieee.org
3-D hand pose estimation is an essential problem for human-computer interaction. Most of
the existing depth-based hand pose estimation methods consume 2-D depth map or 3-D …

Multi-resolution attention convolutional neural network for crowd counting

Y Zhang, C Zhou, F Chang, AC Kot - Neurocomputing, 2019 - Elsevier
Estimating crowd counts remains a challenging task due to the problems of scale variations,
non-uniform distribution and complex backgrounds. In this paper, we propose a multi …

Gan-based virtual-to-real image translation for urban scene semantic segmentation

X Guo, Z Wang, Q Yang, W Lv, X Liu, Q Wu, J Huang - Neurocomputing, 2020 - Elsevier
Semantic image segmentation requires large amounts of pixel-wise labeled training data.
Creating such data generally requires labor-intensive human manual annotation. Thus …