期刊
IEEE ACCESS
卷 10, 期 -, 页码 94354-94362出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3200037
关键词
Deep learning; Visualization; Solid modeling; Feature extraction; Face recognition; Predictive models; Deep learning; Convolutional neural networks; Face alignment; graph convolutional network; high resolution net; heatmap
资金
- Basic Science Research Program through the National Research Foundation of Korea (NRF) through the Ministry of Education [2020R1A6A1A03038540]
- Korea Institute of Planning and Evaluation for Technology in Food, Agriculture, Forestry and Fisheries (IPET) through the Digital Breeding Transformation Technology Development Program - Ministry of Agriculture, Food and Rural Affairs (MAFRA) [322063-03-1-SB010]
- Ministry of SMEs and Startups (MSS), South Korea, through the Technology Development Program [RS-2022-00156456]
The conventional heatmap regression with deep networks has achieved success in landmark detection, but fails to fully exploit the overall structure of landmarks. This paper proposes a new landmark detection method that models landmarks as a graph structure, enabling the capture of the overall structure. Experimental results demonstrate the robustness of the proposed method.
The conventional heatmap regression with deep networks has become one of the mainstream approaches for landmark detection. Despite their success, these methods do not exploit the overall landmarks structure. We present a new landmark detection which is capable to capture the overall structure of landmarks by modeling these landmarks as a graph structure. Our method combines a deep heatmap regression network with Graph Convolutional Network (GCN) into an end-to-end differentiable model. The proposed method can utilize both visual information and overall landmarks structure to localize landmarks from an image. The ad hoc spatial relationships between landmarks are learned naturally with GCN network. Experiments on multiple datasets show the robustness of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据