Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Hyunduk | - |
dc.contributor.author | Lee, Sang-Heon | - |
dc.contributor.author | Sohn, Myoung-Kyu | - |
dc.date.accessioned | 2023-07-12T10:40:26Z | - |
dc.date.available | 2023-07-12T10:40:26Z | - |
dc.date.created | 2023-04-07 | - |
dc.date.issued | 2023-03 | - |
dc.identifier.issn | 2586-0852 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/46118 | - |
dc.description.abstract | In this paper, we present 3D facial landmarks detection and head pose estimation algorithms. To solve these two tasks simultaneously, we apply the multi-task learning technique. Our architecture consists of three components: a multi-head to deal with different tasks, a backbone to represent common features, and linear layers to output results. For the real-time process, we apply MobileViT as a backbone network. Moreover, we employ the PCGrad algorithm for stable convergence during training. To evaluate the performance of the proposed algorithm, we trained and tested on AFLW200-3D datasets, respectively. In the experiments, we demonstrate the experimental results for comparing the accuracy between MobileNetV3 and MobileViT. | - |
dc.language | English | - |
dc.publisher | Journal of Industrial Information Technology and Application | - |
dc.title | 3D facial Landmarks Detection and Head Pose Estimation using Multi-task Learning and Vision Transformer | - |
dc.type | Article | - |
dc.identifier.doi | 10.22664/ISITA.2021.7.1.666 | - |
dc.identifier.bibliographicCitation | Journal of Industrial Information Technology and Application, v.7, no.1, pp.666 - 670 | - |
dc.description.isOpenAccess | TRUE | - |
dc.subject.keywordAuthor | 3d facial landmarks detection | - |
dc.subject.keywordAuthor | head pose estimation, multi-task learning | - |
dc.subject.keywordAuthor | vision transformer | - |
dc.citation.endPage | 670 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 666 | - |
dc.citation.title | Journal of Industrial Information Technology and Application | - |
dc.citation.volume | 7 | - |