English

Attention! A Lightweight 2D Hand Pose Estimation Approach

Computer Vision and Pattern Recognition 2020-06-02 v2 Human-Computer Interaction Machine Learning

Abstract

Vision based human pose estimation is an non-invasive technology for Human-Computer Interaction (HCI). Direct use of the hand as an input device provides an attractive interaction method, with no need for specialized sensing equipment, such as exoskeletons, gloves etc, but a camera. Traditionally, HCI is employed in various applications spreading in areas including manufacturing, surgery, entertainment industry and architecture, to mention a few. Deployment of vision based human pose estimation algorithms can give a breath of innovation to these applications. In this letter, we present a novel Convolutional Neural Network architecture, reinforced with a Self-Attention module that it can be deployed on an embedded system, due to its lightweight nature, with just 1.9 Million parameters. The source code and qualitative results are publicly available.

Keywords

Cite

@article{arxiv.2001.08047,
  title  = {Attention! A Lightweight 2D Hand Pose Estimation Approach},
  author = {Nicholas Santavas and Ioannis Kansizoglou and Loukas Bampis and Evangelos Karakasis and Antonios Gasteratos},
  journal= {arXiv preprint arXiv:2001.08047},
  year   = {2020}
}

Comments

updated version with ablation studies

R2 v1 2026-06-23T13:17:42.837Z