| Issue |
E3S Web Conf.
Volume 218, 2020
2020 International Symposium on Energy, Environmental Science and Engineering (ISEESE 2020)
|
|
|---|---|---|
| Article Number | 03023 | |
| Number of page(s) | 4 | |
| Section | Environmental Chemistry and Environmental Pollution Analysis and Control | |
| DOI | https://doi.org/10.1051/e3sconf/202021803023 | |
| Published online | 11 December 2020 | |
Multihead Self Attention Hand Pose Estimation
1
School of Computer Science, Wuhan Donghu University, Wuhan, China
2
School of Computer Science, Wuhan Qingchuan University, Wuhan, China
* Corresponding author’s e-mail: 25879030@qq.com
In This paper, we propose a hand pose estimation neural networks architecture named MSAHP which can improve PCK (percentage correct keypoints) greatly by fusing self-attention module in CNN (Convolutional Neural Networks). The proposed network is based on a ResNet (Residual Neural Network) backbone and concatenate discriminative features through multiple different scale feature maps, then multiple head self-attention module was used to focus on the salient feature map area. In recent years, self-attention mechanism was applicated widely in NLP and speech recognition, which can improve greatly key metrics. But in compute vision especially for hand pose estimation, we did not find the application. Experiments on hand pose estimation dataset demonstrate the improved PCK of our MSAHP than the existing state-of-the-art hand pose estimation methods. Specifically, the proposed method can achieve 93.68% PCK score on our mixed test dataset.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.