Residual attention regression for 3D hand pose estimation

Jing Li, Long Zhang, Zhaojie Ju*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

89 Downloads (Pure)

Abstract

3D hand pose estimation is an important and challenging task for virtual reality and human-computer interaction. In this paper, we propose a simple and effective residual attention regression model for accurate 3D hand pose estimation from a depth image. The model is trained in an end-to-end fashion. Specifically, we stack different attention modules to capture different types of attention-aware features, and then implement physical constraints of the hand by projecting the pose parameters into a lower-dimensional space. In this way, 3D coordinates of hand joints are estimated directly. The experimental results demonstrate that our proposed residual attention network can achieve superior or comparable performance on three main challenging datasets, where the average 3D error is 9.7 mm on the MSRA dataset, 7.8 mm on the ICVL dataset, and 17.6 mm on the NYU dataset.

Original languageEnglish
Title of host publicationIntelligent Robotics and Applications
Subtitle of host publication12th International Conference, ICIRA 2019, Shenyang, China, August 8–11, 2019, Proceedings, Part IV
EditorsHaibin Yu, Jinguo Liu, Lianqing Liu, Zhaojie Ju, Yuwang Liu, Dalin Zhou
PublisherSpringer
Chapter52
Pages605-614
Number of pages10
ISBN (Electronic)978-3-030-27538-9
ISBN (Print)978-3-030-27537-2
DOIs
Publication statusPublished - 3 Aug 2019
Event12th International Conference on Intelligent Robotics and Applications - Shenyang, China
Duration: 8 Aug 201911 Aug 2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11743
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameLecture Notes in Artificial Intelligence
PublisherSpringer
Volume11743
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference12th International Conference on Intelligent Robotics and Applications
Abbreviated titleICIRA 2019
Country/TerritoryChina
CityShenyang
Period8/08/1911/08/19

Keywords

  • 3D hand pose estimation
  • Attention mechanism
  • Convolutional neural network
  • Depth images

Fingerprint

Dive into the research topics of 'Residual attention regression for 3D hand pose estimation'. Together they form a unique fingerprint.

Cite this