Semi-supervised Human Pose Estimation Piloted by Manifold Structure
文献类型：会议论文
| 作者 | YongAn Li; Kui Jia; GuiDong Zhang |
| 出版日期 | 2009 |
| 会议名称 | 2009 International Conference on Information Engineering and Computer Science, ICIECS 2009 |
| 会议地点 | Hong Kong |
| 英文摘要 | In recent papers, mixture of experts is used to overcome the ambiguities occurred in 3D human pose estimation from monocular images or videos. However, because of the high dimension of the image and pose space, a large amount of labeled samples are required during estimation, i.e. images with their corresponding poses, this demands considerable human effort. In this paper, we use a semi-supervised style that utilizes both labeled and unlabelled samples to deal with the task. Manifold regularization is introduced as prior information to pilot each expert. Experimental results in real image sequences illustrate that our framework truly works well. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/2456]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2009 |
| 推荐引用方式 GB/T 7714 | YongAn Li,Kui Jia,GuiDong Zhang. Semi-supervised Human Pose Estimation Piloted by Manifold Structure[C]. 见:2009 International Conference on Information Engineering and Computer Science, ICIECS 2009. Hong Kong. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
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。