Show simple item record

dc.contributor.author
Zhang, Xucong
dc.contributor.author
Sugano, Yusuke
dc.contributor.author
Bulling, Andreas
dc.contributor.author
Hilliges, Otmar
dc.date.accessioned
2021-01-12T14:04:38Z
dc.date.available
2020-12-08T08:51:05Z
dc.date.available
2021-01-12T14:04:38Z
dc.date.issued
2020-09-10
dc.identifier.uri
http://hdl.handle.net/20.500.11850/455196
dc.identifier.doi
10.3929/ethz-b-000455196
dc.description.abstract
Traditionally, appearance-based gaze estimation methods use statically defined face regions as input to the gaze estimator, such as eye patches, and therefore suffer from difficult lighting conditions and extreme head poses for which these regions are often not the most informative with respect to the gaze estimation task. We posit that facial regions should be selected dynamically based on the image content and propose a novel gaze estimation method that combines the task of region proposal and gaze estimation into a single end-to-end trainable framework. We introduce a novel loss that allows for unsupervised training of a region proposal network alongside the (supervised) training of the final gaze estimator. We show that our method can learn meaningful region selection strategies and outperforms fixed region approaches. We further show that our method performs particularly well for challenging cases, i.e., those with difficult lighting conditions such as directional lights, extreme head angles, or self-occlusion. Finally, we show that the proposed method achieves better results than the current state-of-the-art method in within and cross-dataset evaluations.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
British Machine Vision Association
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.title
Learning-based Region Selection for End-to-End Gaze Estimation
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
ethz.book.title
31st British Machine Vision Conference (BMVC 2020)
en_US
ethz.pages.start
86
en_US
ethz.size
13 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.event
31st British Machine Vision Conference (BMVC 2020) (virtual)
en_US
ethz.event.location
Manchester, United Kingdom
en_US
ethz.event.date
September 7-10, 2020
en_US
ethz.notes
Poster presentation on September 10, 2020. Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.publication.place
s.l.
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02658 - Inst. Intelligente interaktive Systeme / Inst. Intelligent Interactive Systems::03979 - Hilliges, Otmar / Hilliges, Otmar
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02658 - Inst. Intelligente interaktive Systeme / Inst. Intelligent Interactive Systems::03979 - Hilliges, Otmar / Hilliges, Otmar
ethz.relation.isPartOf
https://www.bmvc2020-conference.com/programme/accepted-papers/
ethz.date.deposited
2020-12-08T08:51:16Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-01-12T14:05:07Z
ethz.rosetta.lastUpdated
2021-02-15T23:09:43Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Learning-based%20Region%20Selection%20for%20End-to-End%20Gaze%20Estimation&rft.date=2020-09-10&rft.spage=86&rft.au=Zhang,%20Xucong&Sugano,%20Yusuke&Bulling,%20Andreas&Hilliges,%20Otmar&rft.genre=proceeding&rft.btitle=31st%20British%20Machine%20Vision%20Conference%20(BMVC%202020)
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record