Towards Part-Aware Monocular 3D Human Pose Estimation: An Architecture Search Approach | |
Chen, Zerui1,3; Huang, Yan1; Yu, Hongyuan1,3; Xue, Bin3; Han, Ke1; Guo, Yiru5; Wang, Liang1,2,4 | |
2020-08 | |
会议名称 | European Conference on Computer Vision |
会议日期 | 2020.8.24-2020.8.28 |
会议地点 | Online |
摘要 | Even though most existing monocular 3D pose estimation approaches achieve very competitive results, they ignore the heterogeneity among human body parts by estimating them with the same network architecture. To accurately estimate 3D poses of different body parts, we attempt to build a part-aware 3D pose estimator by searching a set of network architectures. Consequently, our model automatically learns to select a suitable architecture to estimate each body part. Compared to models built on the commonly used ResNet-50 backbone, it reduces 62% parameters and achieves better performance. With roughly the same computational complexity as previous models, our approach achieves state-of-the-art results on both the single-person and multi-person 3D pose estimation benchmarks. |
收录类别 | EI |
七大方向——子方向分类 | 机器学习 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44425 |
专题 | 智能感知与计算 |
通讯作者 | Chen, Zerui |
作者单位 | 1.Center for Research on Intelligent Perception and Computing, NLPR, CASIA 2.Center for Excellence in Brain Science and Intelligence Technology, CAS 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.Chinese Academy of Sciences, Artificial Intelligence Research (CAS-AIR) 5.School of Astronautics, Beihang University |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Chen, Zerui,Huang, Yan,Yu, Hongyuan,et al. Towards Part-Aware Monocular 3D Human Pose Estimation: An Architecture Search Approach[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Towards Part-Aware M(2120KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论