DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fan, Di | ko |
dc.contributor.author | Kim, Hyunwoo | ko |
dc.contributor.author | Kim, Junmo | ko |
dc.contributor.author | Liu, Yunhui | ko |
dc.contributor.author | Huang, Qiang | ko |
dc.date.accessioned | 2019-07-23T06:21:19Z | - |
dc.date.available | 2019-07-23T06:21:19Z | - |
dc.date.created | 2019-07-23 | - |
dc.date.created | 2019-07-23 | - |
dc.date.issued | 2019-06 | - |
dc.identifier.citation | APPLIED SCIENCES-BASEL, v.9, no.12 | - |
dc.identifier.issn | 2076-3417 | - |
dc.identifier.uri | http://hdl.handle.net/10203/263748 | - |
dc.description.abstract | Face attributes prediction has an increasing amount of applications in human-computer interaction, face verification and video surveillance. Various studies show that dependencies exist in face attributes. Multi-task learning architecture can build a synergy among the correlated tasks by parameter sharing in the shared layers. However, the dependencies between the tasks have been ignored in the task-specific layers of most multi-task learning architectures. Thus, how to further boost the performance of individual tasks by using task dependencies among face attributes is quite challenging. In this paper, we propose a multi-task learning using task dependencies architecture for face attributes prediction and evaluate the performance with the tasks of smile and gender prediction. The designed attention modules in task-specific layers of our proposed architecture are used for learning task-dependent disentangled representations. The experimental results demonstrate the effectiveness of our proposed network by comparing with the traditional multi-task learning architecture and the state-of-the-art methods on Faces of the world (FotW) and Labeled faces in the wild-a (LFWA) datasets. | - |
dc.language | English | - |
dc.publisher | MDPI | - |
dc.title | Multi-Task Learning Using Task Dependencies for Face Attributes Prediction | - |
dc.type | Article | - |
dc.identifier.wosid | 000473754800144 | - |
dc.identifier.scopusid | 2-s2.0-85068149943 | - |
dc.type.rims | ART | - |
dc.citation.volume | 9 | - |
dc.citation.issue | 12 | - |
dc.citation.publicationname | APPLIED SCIENCES-BASEL | - |
dc.identifier.doi | 10.3390/app9122535 | - |
dc.contributor.localauthor | Kim, Junmo | - |
dc.contributor.nonIdAuthor | Fan, Di | - |
dc.contributor.nonIdAuthor | Kim, Hyunwoo | - |
dc.contributor.nonIdAuthor | Liu, Yunhui | - |
dc.contributor.nonIdAuthor | Huang, Qiang | - |
dc.description.isOpenAccess | Y | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | multi-task learning | - |
dc.subject.keywordAuthor | task dependencies | - |
dc.subject.keywordAuthor | attention | - |
dc.subject.keywordAuthor | face attributes prediction | - |
dc.subject.keywordAuthor | deep convolutional neural network | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.