File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: AGSS-VOS: Attention guided single-shot video object segmentation

TitleAGSS-VOS: Attention guided single-shot video object segmentation
Authors
Lin, HuaijiaQi, XiaojuanJia, Jiaya
Issue Date2019
Citation
Proceedings of the IEEE International Conference on Computer Vision, 2019, v. 2019-October, p. 3948-3956 How to Cite?
DOI: http://dx.doi.org/10.1109/ICCV.2019.00405
Abstract© 2019 IEEE. Most video object segmentation approaches process objects separately. This incurs high computational cost when multiple objects exist. In this paper, we propose AGSS-VOS to segment multiple objects in one feed-forward path via instance-agnostic and instance-specific modules. Information from the two modules is fused via an attention-guided decoder to simultaneously segment all object instances in one path. The whole framework is end-to-end trainable with instance IoU loss. Experimental results on Youtube- VOS and DAVIS-2017 dataset demonstrate that AGSS-VOS achieves competitive results in terms of both accuracy and efficiency.
Persistent Identifierhttp://hdl.handle.net/10722/281975
ISSN
1550-5499
2023 SCImago Journal Rankings: 12.263
ISI Accession Number ID
WOS:000531438104010

 

DC FieldValueLanguage
dc.contributor.authorLin, Huaijia-
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2020-04-09T09:19:16Z-
dc.date.available2020-04-09T09:19:16Z-
dc.date.issued2019-
dc.identifier.citationProceedings of the IEEE International Conference on Computer Vision, 2019, v. 2019-October, p. 3948-3956-
dc.identifier.issn1550-5499-
dc.identifier.urihttp://hdl.handle.net/10722/281975-
dc.description.abstract© 2019 IEEE. Most video object segmentation approaches process objects separately. This incurs high computational cost when multiple objects exist. In this paper, we propose AGSS-VOS to segment multiple objects in one feed-forward path via instance-agnostic and instance-specific modules. Information from the two modules is fused via an attention-guided decoder to simultaneously segment all object instances in one path. The whole framework is end-to-end trainable with instance IoU loss. Experimental results on Youtube- VOS and DAVIS-2017 dataset demonstrate that AGSS-VOS achieves competitive results in terms of both accuracy and efficiency.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE International Conference on Computer Vision-
dc.titleAGSS-VOS: Attention guided single-shot video object segmentation-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICCV.2019.00405-
dc.identifier.scopuseid_2-s2.0-85081922935-
dc.identifier.volume2019-October-
dc.identifier.spage3948-
dc.identifier.epage3956-
dc.identifier.isiWOS:000531438104010-
dc.identifier.issnl1550-5499-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats