Loading...
Loading...

Go to the content (press return)

Residual attention graph convolutional network for geometric 3D scene classification

Author
Mosella, A.; Ruiz-Hidalgo, J.
Type of activity
Presentation of work at congresses
Name of edition
IEEE International Conference on Computer Vision Workshops 2019
Date of publication
2019
Presentation's date
2019-11-01
Book of congress proceedings
2019 International Conference on Computer Vision ICCV 2019: proceedings: 27 October - 2 November 2019 Seoul, Korea
First page
4123
Last page
4132
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
10.1109/ICCVW.2019.00507
Project funding
MALEGRA, TEC2016-75976-R
Repository
http://hdl.handle.net/2117/184046 Open in new window
Abstract
Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible errors due to missing local geometric context in the depth channel. This work proposes a novel Residual Attention Graph Convolutional Network that exploits the intrinsic geometric context inside a 3D space without using any kind of point features, allowing the use of organized ...
Citation
Mosella, A.; Ruiz-Hidalgo, J. Residual attention graph convolutional network for geometric 3D scene classification. A: IEEE International Conference on Computer Vision Workshops. "2019 International Conference on Computer Vision ICCV 2019: proceedings: 27 October - 2 November 2019 Seoul, Korea". Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 4123-4132.
Keywords
Convolution, Image edge detection, Neural networks, Sensors, Standards, Task analysis, Three-dimensional displays
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants