File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Facial Landmark Localization in the Wild by Backbone-Branches Representation Learning

TitleFacial Landmark Localization in the Wild by Backbone-Branches Representation Learning
Authors
Issue Date2018
PublisherIEEE.
Citation
Fourth IEEE International Conference on Multimedia Big Data (BigMM), Xi'an, China, 13-16 September 2018. In 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM), p. 1-8 How to Cite?
AbstractFacial landmark localization plays a critical role in face recognition and analysis. In this paper, we propose a novel cascaded Backbone-Branches Fully Convolutional Neural Network (BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings. Our proposed BB-FCN generates facial landmark response maps directly from raw images without any pre-processing. It follows a coarse-to-fine cascaded pipeline, which consists of a backbone network for roughly detecting the locations of all facial landmarks and one branch network for each type of detected landmarks for further refining their locations. Extensive experimental evaluations demonstrate that our proposed BB-FCN can significantly outperform the state of the art under both constrained (i.e. within detected facial regions only) and unconstrained settings.
Persistent Identifierhttp://hdl.handle.net/10722/259644
ISBN

 

DC FieldValueLanguage
dc.contributor.authorLiu, L-
dc.contributor.authorLi, G-
dc.contributor.authorXie, Y-
dc.contributor.authorLin, L-
dc.contributor.authorYu, Y-
dc.date.accessioned2018-09-03T04:11:22Z-
dc.date.available2018-09-03T04:11:22Z-
dc.date.issued2018-
dc.identifier.citationFourth IEEE International Conference on Multimedia Big Data (BigMM), Xi'an, China, 13-16 September 2018. In 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM), p. 1-8-
dc.identifier.isbn9781538653210-
dc.identifier.urihttp://hdl.handle.net/10722/259644-
dc.description.abstractFacial landmark localization plays a critical role in face recognition and analysis. In this paper, we propose a novel cascaded Backbone-Branches Fully Convolutional Neural Network (BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings. Our proposed BB-FCN generates facial landmark response maps directly from raw images without any pre-processing. It follows a coarse-to-fine cascaded pipeline, which consists of a backbone network for roughly detecting the locations of all facial landmarks and one branch network for each type of detected landmarks for further refining their locations. Extensive experimental evaluations demonstrate that our proposed BB-FCN can significantly outperform the state of the art under both constrained (i.e. within detected facial regions only) and unconstrained settings.-
dc.languageeng-
dc.publisherIEEE.-
dc.relation.ispartof2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)-
dc.rights2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM). Copyright © IEEE.-
dc.titleFacial Landmark Localization in the Wild by Backbone-Branches Representation Learning-
dc.typeConference_Paper-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/BigMM.2018.8499059-
dc.identifier.hkuros288482-
dc.identifier.spage1-
dc.identifier.epage8-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats