Loading...
Loading...

Go to the content (press return)

RVOS: end-to-end recurrent network for video object segmentation

Author
Ventura, C.; Bellver, M.; Girbau, A.; Salvador, A.; Marques, F.; Giro, X.
Type of activity
Presentation of work at congresses
Name of edition
2019 IEEE Conference on Computer Vision and Pattern Recognition
Date of publication
2019
Presentation's date
2019-06-19
Book of congress proceedings
CVPR 2019: Conference on Computer Vision and Pattern Recognition: Long Beach, CA: June 16-20, 2019
First page
5277
Last page
5286
Publisher
Computer Vision Foundation
Project funding
Models de programació i entorns d'execució paral·lels
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/166919 Open in new window
https://arxiv.org/abs/1903.05612 Open in new window
URL
http://openaccess.thecvf.com/content_CVPR_2019/html/Ventura_RVOS_End-To-End_Recurrent_Network_for_Video_Object_Segmentation_CVPR_2019_paper.html Open in new window
Abstract
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a fr...
Citation
Ventura, C. [et al.]. RVOS: end-to-end recurrent network for video object segmentation. A: IEEE Conference on Computer Vision and Pattern Recognition. "CVPR 2019: Conference on Computer Vision and Pattern Recognition: Long Beach, CA: June 16-20, 2019". Computer Vision Foundation, 2019, p. 5277-5286.
Keywords
Computer vision, Deep learning, Video object segmentation
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments