Zur Kurzanzeige

dc.contributor.author
Robinson, Andreas
dc.contributor.author
Lawin, Felix J.
dc.contributor.author
Danelljan, Martin
dc.contributor.author
Khan, Fahad S.
dc.contributor.author
Felsberg, Michael
dc.date.accessioned
2021-01-11T15:14:35Z
dc.date.available
2021-01-10T21:33:26Z
dc.date.available
2021-01-11T15:14:35Z
dc.date.issued
2020
dc.identifier.isbn
978-1-7281-7168-5
en_US
dc.identifier.isbn
978-1-7281-7169-2
en_US
dc.identifier.other
10.1109/cvpr42600.2020.00743
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/460906
dc.description.abstract
Video object segmentation (VOS) is a highly challenging problem since the initial mask, defining the target object, is only given at test-time. The main difficulty is to effectively handle appearance changes and similar background objects, while maintaining accurate segmentation. Most previous approaches fine-tune segmentation networks on the first frame, resulting in impractical frame-rates and risk of overfitting. More recent methods integrate generative target appearance models, but either achieve limited robustness or require large amounts of training data. We propose a novel VOS architecture consisting of two network components. The target appearance model consists of a light-weight module, which is learned during the inference stage using fast optimization techniques to predict a coarse but robust target segmentation. The segmentation model is exclusively trained offline, designed to process the coarse scores into high quality segmentation masks. Our method is fast, easily trainable and remains highly effective in cases of limited training data. We perform extensive experiments on the challenging YouTube-VOS and DAVIS datasets. Our network achieves favorable performance, while operating at higher frame-rates compared to state-of-the-art. Code and trained models are available at https://github.com/andr345/frtm-vos.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
Learning Fast and Robust Target Models for Video Object Segmentation
en_US
dc.type
Conference Paper
dc.date.published
2020-08-05
ethz.book.title
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
en_US
ethz.pages.start
7404
en_US
ethz.pages.end
7413
en_US
ethz.event
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020) (virtual)
en_US
ethz.event.location
Seattle, WA, USA
en_US
ethz.event.date
June 13-19, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
en_US
ethz.date.deposited
2021-01-10T21:33:32Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-01-11T15:14:43Z
ethz.rosetta.lastUpdated
2021-02-15T23:07:26Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Learning%20Fast%20and%20Robust%20Target%20Models%20for%20Video%20Object%20Segmentation&rft.date=2020&rft.spage=7404&rft.epage=7413&rft.au=Robinson,%20Andreas&Lawin,%20Felix%20J.&Danelljan,%20Martin&Khan,%20Fahad%20S.&Felsberg,%20Michael&rft.isbn=978-1-7281-7168-5&978-1-7281-7169-2&rft.genre=proceeding&rft_id=info:doi/10.1109/cvpr42600.2020.00743&rft.btitle=2020%20IEEE/CVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20(CVPR)
 Printexemplar via ETH-Bibliothek suchen

Dateien zu diesem Eintrag

DateienGrößeFormatIm Viewer öffnen

Zu diesem Eintrag gibt es keine Dateien.

Publikationstyp

Zur Kurzanzeige