Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/143257
Full metadata record
DC FieldValueLanguage
dc.contributor.authorXiao, Huaxinen_US
dc.contributor.authorFeng, Jiashien_US
dc.contributor.authorLin, Guoshengen_US
dc.contributor.authorLiu, Yuen_US
dc.contributor.authorZhang, Maojunen_US
dc.date.accessioned2020-08-17T05:05:16Z-
dc.date.available2020-08-17T05:05:16Z-
dc.date.issued2018-
dc.identifier.citationXiao, H., Feng, J., Lin, G., Liu, Y. & Zhang, M. (2018). MoNet : deep motion exploitation for video object segmentation. Proceedings of the 2018 IEEE/CVF Conference o Computer Vision and Pattern Recognition (2018 CVPR). doi:10.1109/CVPR.2018.00125en_US
dc.identifier.isbn978-1-5386-6421-6-
dc.identifier.urihttps://hdl.handle.net/10356/143257-
dc.description.abstractIn this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i.e., frame representation learning and segmentation refinement. Concretely, MoNet exploits computed motion cue (i.e., optical flow) to reinforce the representation of the target frame by aligning and integrating representations from its neighbors. The new representation provides valuable temporal contexts for segmentation and improves robustness to various common contaminating factors, e.g., motion blur, appearance variation and deformation of video objects. Moreover, MoNet exploits motion inconsistency and transforms such motion cue into foreground/background prior to eliminate distraction from confusing instances and noisy regions. By introducing a distance transform layer, MoNet can effectively separate motion-inconstant instances/regions and thoroughly refine segmentation results. Integrating the proposed two motion exploitation components with a standard segmentation network, MoNet provides new state-of-the-art performance on three competitive benchmark datasets.en_US
dc.description.sponsorshipMinistry of Education (MOE)en_US
dc.language.isoenen_US
dc.rights© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/CVPR.2018.00125.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleMoNet : deep motion exploitation for video object segmentationen_US
dc.typeConference Paperen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.contributor.conference2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018 CVPR)en_US
dc.identifier.doi10.1109/CVPR.2018.00125-
dc.description.versionAccepted versionen_US
dc.identifier.scopus2-s2.0-85062869824-
dc.identifier.spage1140en_US
dc.identifier.epage1148en_US
dc.subject.keywordsMotion Segmentationen_US
dc.subject.keywordsFeature Extractionen_US
dc.citation.conferencelocationSalt Lake City, UT, USAen_US
dc.description.acknowledgementHuaxin Xiao was supported by the China Scholarship Council under Grant 201603170287. Jiashi Feng was partially supported by NUS startup R-263-000-C08-133, MOE Tier-I R-263-000-C21-112, NUS IDS R-263-000-C67-646 and ECRA R-263-000-C87-133.en_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:SCSE Conference Papers
Files in This Item:
File Description SizeFormat 
MoNet- Deep Motion Exploitation for Video Object Segmentation.pdf6.1 MBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 5

107
Updated on Mar 21, 2024

Web of ScienceTM
Citations 5

65
Updated on Oct 30, 2023

Page view(s)

302
Updated on Mar 27, 2024

Download(s) 50

139
Updated on Mar 27, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.