DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Sangbum | ko |
dc.contributor.author | Choi, Seokeon | ko |
dc.contributor.author | Kim, Changick | ko |
dc.date.accessioned | 2021-06-25T04:51:09Z | - |
dc.date.available | 2021-06-25T04:51:09Z | - |
dc.date.created | 2021-06-23 | - |
dc.date.created | 2021-06-23 | - |
dc.date.issued | 2021-06 | - |
dc.identifier.citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.2328 - 2338 | - |
dc.identifier.issn | 2160-7508 | - |
dc.identifier.uri | http://hdl.handle.net/10203/286230 | - |
dc.description.abstract | Currently, 3D pose estimation methods are not compatible with a variety of low computational power devices because of efficiency and accuracy. In this paper, we revisit a pose estimation architecture from a viewpoint of both efficiency and accuracy. We propose a mobile-friendly model, MobileHumanPose, for real-time 3D human pose estimation from a single RGB image. This model consists of the modified MobileNetV2 backbone, a parametric activation function, and the skip concatenation inspired by U-Net. Especially, the skip concatenation structure improves accuracy by propagating richer features with negligible computational power. Our model achieves not only comparable performance to the state-of-the-art models but also has a seven times smaller model size compared to the ResNet-50 based model. In addition, our extra small model reduces inference time by 12.2ms on Galaxy S20 CPU, which is suitable for real-time 3D human pose estimation in mobile applications. The source code is available at: https://github.com/SangbumChoi/MobileHumanPose. | - |
dc.language | English | - |
dc.publisher | IEEE Conference on Computer Vision and Pattern Recognition | - |
dc.title | MobileHumanPose: Toward Real-Time 3D Human Pose Estimation in Mobile Devices | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85115991654 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 2328 | - |
dc.citation.endingpage | 2338 | - |
dc.citation.publicationname | IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.identifier.doi | 10.1109/CVPRW53098.2021.00265 | - |
dc.contributor.localauthor | Kim, Changick | - |
dc.contributor.nonIdAuthor | Choi, Sangbum | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.