Conference item icon

Conference item : Poster

Betrayed by motion: Camouflaged object discovery via motion segmentation

Abstract:

The objective of this paper is to design a computational architecture that discovers camouflaged objects in videos, specifically by exploiting motion information to perform object segmentation. We make the following three contributions: (i) We propose a novel architecture that consists of two essential components for breaking camouflage, namely, a differentiable registration module to align consecutive frames based on the background, which effectively emphasises the object boundary in the dif...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Authors


More by this author
Division:
MPLS
Department:
Engineering Science
Role:
Author
More from this funder
Name:
Engineering and Physical Sciences Research Council
Grant:
EP/M013774/1
Publisher:
Springer
Host title:
Computer Vision – ACCV 2020, Part II
Series:
Image Processing, Computer Vision, Pattern Recognition, and Graphics
Series number:
12623
Journal:
Lecture Notes in Computer Science More from this journal
Pages:
488-503
Publication date:
2021-04-02
Acceptance date:
2020-09-16
Event title:
Asian Conference on Computer Vision, 2020
Event location:
Online
Event website:
http://accv2020.kyoto/
Event start date:
2020-11-30
Event end date:
2020-12-04
DOI:
ISSN:
0302-9743
EISBN:
978-3-030-69532-3
ISBN:
978-3-030-69531-6
Language:
English
Keywords:
Subtype:
Poster
Pubs id:
1140248
Local pid:
pubs:1140248
Deposit date:
2020-11-02

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP