Joint Space Learning for Video-based Face Recognition
文献类型：会议论文
| 作者 | Cao Dong(曹冬) ; Ran He(赫然); Zhenan Sun; Tieniu Tan
|
| 出版日期 | 2015 |
| 会议日期 | 2015 |
| 会议地点 | Kuala Lumpur, Malaysia |
| 关键词 | Video-based Face Recognition Joint Space Learning Randomized Techniques |
| 英文摘要 | Popularity of surveillance and mobile cameras provides great opportunities to video-based face recognition (VFR) in less-controlled conditions. This paper proposes a joint space learning method to simultaneously identify the most representative samples and discriminative features from facial videos for reliable face recognition. Specifically, we use a mixture modal by learning multiple feature spaces to capture the data variations where the representative samples in each subspace are learned. Actually, this procedure is a chick to egg problem and an alternate algorithm is developed to monotonically optimize the joint task. In addition, randomized techniques are applied to kernel approximations for capturing the nonlinear structure in data, so that both accuracy and efficiency of our method can be improved. The proposed method performs better than the state-of-the-art video based face recognition methods on Honda, Mobo and YouTube Celebrities databases. |
| 会议录 | The 3rd IAPR Asian Conference on Pattern Recognition
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/11841]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Tieniu Tan |
| 作者单位 | 模式识别国家重点实验室, 中国科学院自动化研究所 |
| 推荐引用方式 GB/T 7714 | Cao Dong,Ran He,Zhenan Sun,et al. Joint Space Learning for Video-based Face Recognition[C]. 见:. Kuala Lumpur, Malaysia. 2015. |
入库方式： OAI收割
来源：自动化研究所
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。