Region ensemble network: Improving convolutional network for hand pose estimation

H Guo, G Wang, X Chen, C Zhang… - … conference on image …, 2017 - ieeexplore.ieee.org
Hand pose estimation from monocular depth images is an important and challenging
problem for human-computer interaction. Recently deep convolutional networks (ConvNet) …

Region ensemble network: Towards good practices for deep 3D hand pose estimation

G Wang, X Chen, H Guo, C Zhang - Journal of Visual Communication and …, 2018 - Elsevier
Abstract 3D hand pose estimation is an important and challenging problem for human-
computer interaction. Recently convolutional networks (ConvNet) with sophisticated design …

Towards good practices for deep 3d hand pose estimation

H Guo, G Wang, X Chen, C Zhang - arxiv preprint arxiv:1707.07248, 2017 - arxiv.org
3D hand pose estimation from single depth image is an important and challenging problem
for human-computer interaction. Recently deep convolutional networks (ConvNet) with …

Bi-stream pose-guided region ensemble network for fingertip localization from stereo images

G Wang, C Zhang, X Chen, X Ji… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
In human-computer interaction, it is important to accurately estimate the hand pose,
especially fingertips. However, traditional approaches to fingertip localization mainly rely on …

[PDF][PDF] Bi-stream Region Ensemble Network: Promoting Accuracy in Fingertip Localization from Stereo Images.

C Zhang, G Wang, X Chen, H Yang - BMVC, 2018 - image.ee.tsinghua.edu.cn
Accurate fingertip localization is an important and challenging problem in Human Computer
Interaction (HCI). Previous research on hand pose estimation are mainly based on depth …

Two-stream binocular network: Accurate near field finger detection based on binocular images

Y Wei, G Wang, C Zhang, H Guo… - 2017 IEEE Visual …, 2017 - ieeexplore.ieee.org
Fingertip detection plays an important role in human computer interaction. Previous works
transform binocular images into depth images. Then depth-based hand pose estimation …