File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/BigMM.2018.8499059
- Scopus: eid_2-s2.0-85057122540
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Facial Landmark Localization in the Wild by Backbone-Branches Representation Learning
Title | Facial Landmark Localization in the Wild by Backbone-Branches Representation Learning |
---|---|
Authors | |
Keywords | backbone-branches Facial landmark unconstrained settings |
Issue Date | 2018 |
Publisher | IEEE. |
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? |
Abstract | Facial 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 Identifier | http://hdl.handle.net/10722/259644 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, L | - |
dc.contributor.author | Li, G | - |
dc.contributor.author | Xie, Y | - |
dc.contributor.author | Lin, L | - |
dc.contributor.author | Yu, Y | - |
dc.date.accessioned | 2018-09-03T04:11:22Z | - |
dc.date.available | 2018-09-03T04:11:22Z | - |
dc.date.issued | 2018 | - |
dc.identifier.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 | - |
dc.identifier.isbn | 9781538653210 | - |
dc.identifier.uri | http://hdl.handle.net/10722/259644 | - |
dc.description.abstract | Facial 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.language | eng | - |
dc.publisher | IEEE. | - |
dc.relation.ispartof | 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) | - |
dc.rights | 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM). Copyright © IEEE. | - |
dc.subject | backbone-branches | - |
dc.subject | Facial landmark | - |
dc.subject | unconstrained settings | - |
dc.title | Facial Landmark Localization in the Wild by Backbone-Branches Representation Learning | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Yu, Y=rp01415 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/BigMM.2018.8499059 | - |
dc.identifier.scopus | eid_2-s2.0-85057122540 | - |
dc.identifier.hkuros | 288482 | - |
dc.identifier.spage | 1 | - |
dc.identifier.epage | 8 | - |
dc.publisher.place | United States | - |