Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/82836
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGe, Liuhaoen
dc.contributor.authorLiang, Huien
dc.contributor.authorYuan, Junsongen
dc.contributor.authorThalmann, Danielen
dc.date.accessioned2019-11-14T01:44:46Zen
dc.date.accessioned2019-12-06T15:06:35Z-
dc.date.available2019-11-14T01:44:46Zen
dc.date.available2019-12-06T15:06:35Z-
dc.date.issued2017en
dc.identifier.citationGe, L., Liang, H., Yuan, J., & Thalmann, D. (2017). 3D convolutional neural networks for efficient and robust hand pose estimation from single depth images. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/CVPR.2017.602en
dc.identifier.urihttps://hdl.handle.net/10356/82836-
dc.description.abstractWe propose a simple, yet effective approach for real-time hand pose estimation from single depth images using three-dimensional Convolutional Neural Networks (3D CNNs). Image based features extracted by 2D CNNs are not directly suitable for 3D hand pose estimation due to the lack of 3D spatial information. Our proposed 3D CNN taking a 3D volumetric representation of the hand depth image as input can capture the 3D spatial structure of the input and accurately regress full 3D hand pose in a single pass. In order to make the 3D CNN robust to variations in hand sizes and global orientations, we perform 3D data augmentation on the training data. Experiments show that our proposed 3D CNN based approach outperforms state-of-the-art methods on two challenging hand pose datasets, and is very efficient as our implementation runs at over 215 fps on a standard computer with a single GPU.en
dc.description.sponsorshipNRF (Natl Research Foundation, S’pore)en
dc.description.sponsorshipASTAR (Agency for Sci., Tech. and Research, S’pore)en
dc.description.sponsorshipMOE (Min. of Education, S’pore)en
dc.format.extent10 p.en
dc.language.isoenen
dc.rights© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/CVPR.2017.602en
dc.subjectThree-dimensional Displaysen
dc.subjectPose Estimationen
dc.subjectEngineering::Electrical and electronic engineeringen
dc.title3D convolutional neural networks for efficient and robust hand pose estimation from single depth imagesen
dc.typeConference Paperen
dc.contributor.schoolInterdisciplinary Graduate School (IGS)en
dc.contributor.conference2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.identifier.doi10.1109/CVPR.2017.602en
dc.description.versionAccepted versionen
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:IGS Conference Papers

SCOPUSTM   
Citations

98
Updated on Sep 1, 2020

PublonsTM
Citations

27
Updated on Feb 22, 2021

Page view(s)

104
Updated on Feb 24, 2021

Download(s)

25
Updated on Feb 24, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.