Loading...
Loading...

Go to the content (press return)

One shot learning for generic instance segmentation in RGBD videos

Author
Lin, X.; Casas, J.; Pardas, M.
Type of activity
Presentation of work at congresses
Name of edition
14th International Conference on Computer Vision Theory and Applications
Date of publication
2019
Presentation's date
2019-02-25
Book of congress proceedings
Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
First page
233
Last page
239
Publisher
Scitepress
DOI
10.5220/0007259902330239
Project funding
Heterogeneous information and graph signal processing for the Big Data era. Application to high-throughput, remote sensing, multimedia and human computer interfaces
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/165543 Open in new window
URL
http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0007259902330239 Open in new window
Abstract
Hand-crafted features employed in classical generic instance segmentation methods have limited discriminative power to distinguish different objects in the scene, while Convolutional Neural Networks (CNNs) based semantic segmentation is restricted to predefined semantics and not aware of object instances. In this paper, we combine the advantages of the two methodologies and apply the combined approach to solve a generic instance segmentation problem in RGBD video sequences. In practice, a classi...
Citation
Lin, X.; Casas, J.; Pardas, M. One shot learning for generic instance segmentation in RGBD videos. A: International Conference on Computer Vision Theory and Applications. "Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications". Setúbal: Scitepress, 2019, p. 233-239.
Keywords
Convolutional neural network, Instance segmentation, One shot learning
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments