Dual embedding learning for video instance segmentation

Feng, Q; Yang, Z; Li, P; Wei, Y; Yang, Y

Dual embedding learning for video instance segmentation

Feng, Q

Yang, Z

Li, P

Wei, Y Yang, Y

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019, 2020, 00, pp. 717-720
Issue Date:: 2020

Closed Access

	Filename	Description	Size
	09022433.pdf	Published version	811.04 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Feng, Q https://orcid.org/0000-0003-1014-6081
dc.contributor.author	Yang, Z https://orcid.org/0000-0001-8783-8313
dc.contributor.author	Li, P https://orcid.org/0000-0003-1809-2137
dc.contributor.author	Wei, Y
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.date	2019-10-27
dc.date.accessioned	2021-04-12T11:01:03Z
dc.date.available	2021-04-12T11:01:03Z
dc.date.issued	2020
dc.identifier.citation	Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019, 2020, 00, pp. 717-720
dc.identifier.isbn	9781728150239
dc.identifier.uri	http://hdl.handle.net/10453/148041
dc.description.abstract	© 2019 IEEE. In this paper, we propose a novel framework to generate high-quality segmentation results in a two-stage style, aiming at video instance segmentation task which requires simultaneous detection, segmentation and tracking of instances. To address this multi-task efficiently, we opt to first select high-quality detection proposals in each frame. The categories of the proposals are calibrated with the global context of video. Then, each selected proposal is extended temporally by a bi-directional Instance-Pixel Dual-Tracker (IPDT) which synchronizes the tracking on both instance-level and pixel-level. The instance-level module concentrates on distinguishing the target instance from other objects while the pixel-level module focuses more on the local feature of the instance. Our proposed method achieved a competitive result of mAP 45.0% on the Youtube-VOS dataset, ranking the 3rd in Track 2 of the 2nd Large-scale Video Object Segmentation Challenge.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
dc.relation.ispartof	IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
dc.relation.isbasedon	10.1109/ICCVW.2019.00090
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Dual embedding learning for video instance segmentation
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Seoul, Korea (South)
utslib.for	0801 Artificial Intelligence and Image Processing
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2021-04-12T11:01:02Z
pubs.finish-date	2019-10-28
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2019-10-27
pubs.volume	00
dc.location	Piscataway, USA

Abstract:

© 2019 IEEE. In this paper, we propose a novel framework to generate high-quality segmentation results in a two-stage style, aiming at video instance segmentation task which requires simultaneous detection, segmentation and tracking of instances. To address this multi-task efficiently, we opt to first select high-quality detection proposals in each frame. The categories of the proposals are calibrated with the global context of video. Then, each selected proposal is extended temporally by a bi-directional Instance-Pixel Dual-Tracker (IPDT) which synchronizes the tracking on both instance-level and pixel-level. The instance-level module concentrates on distinguishing the target instance from other objects while the pixel-level module focuses more on the local feature of the instance. Our proposed method achieved a competitive result of mAP 45.0% on the Youtube-VOS dataset, ranking the 3rd in Track 2 of the 2nd Large-scale Video Object Segmentation Challenge.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/148041