Please use this identifier to cite or link to this item:
Title: Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks
Authors: Cai, Yujun
Ge, Liuhao
Liu, Jun
Cai, Jianfei
Cham, Tat-Jen
Yuan, Junsong
Thalmann, Nadia Magnenat
Keywords: 3D Pose Estimation
Graph Convolutional Neural Network (GCN)
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2019
Source: Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T.-J., Yuan, J., & Thalmann, N. M. (2019). Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2272-2281. doi:10.1109/ICCV.2019.00236
Abstract: Despite great progress in 3D pose estimation from single-view images or videos, it remains a challenging task due to the substantial depth ambiguity and severe selfocclusions. Motivated by the effectiveness of incorporating spatial dependencies and temporal consistencies to alleviate these issues, we propose a novel graph-based method to tackle the problem of 3D human body and 3D hand pose estimation from a short sequence of 2D joint detections. Particularly, domain knowledge about the human hand (body) configurations is explicitly incorporated into the graph convolutional operations to meet the specific demand of the 3D pose estimation. Furthermore, we introduce a local-to-global network architecture, which is capable of learning multi-scale features for the graph-based representations. We evaluate the proposed method on challenging benchmark datasets for both 3D hand pose estimation and 3D body pose estimation. Experimental results show that our method achieves state-of-the-art performance on both tasks.
DOI: 10.1109/ICCV.2019.00236
Rights: © 2019 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:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IGS Conference Papers

Files in This Item:
File Description SizeFormat 
1881.pdf2.14 MBAdobe PDFThumbnail


Updated on Jul 21, 2020


Updated on Jan 15, 2021

Page view(s)

Updated on Jan 15, 2021

Download(s) 20

Updated on Jan 15, 2021

Google ScholarTM




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