Multi-view face pose estimation based on supervised ISA learning | |
Li, Stan Z. ; Peng, Xianhuan ; Hou, Xinwen ; Zhang, Hongjiang ; Cheng, Qiansheng | |
2002 | |
英文摘要 | Independent subspace analysis (ISA) is able to learn view-subspaces unsupervisedly from (view-unlabeled) multi-view face examples (S.Z. Li et al., 2001). We explain underlying reasons for the emergent formation of ISA view-subspaces. Based on the analysis, we present a supervised method for more effective learning of view-subspace, assuming that view-labeled face examples are available. The models thus learned give more accurate pose estimation than those obtained with the unsupervised ISA. ? 2002 IEEE.; EI; 0 |
语种 | 英语 |
出处 | EI |
内容类型 | 其他 |
源URL | [http://hdl.handle.net/20.500.11897/330343] |
专题 | 数学科学学院 |
推荐引用方式 GB/T 7714 | Li, Stan Z.,Peng, Xianhuan,Hou, Xinwen,et al. Multi-view face pose estimation based on supervised ISA learning. 2002-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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