CASIA OpenIR  > 智能感知与计算研究中心
Joint Space Learning for Video-based Face Recognition
Cao Dong(曹冬); Ran He(赫然); Zhenan Sun; Tieniu Tan
2015
会议名称The 3rd IAPR Asian Conference on Pattern Recognition
会议录名称The 3rd IAPR Asian Conference on Pattern Recognition
会议日期2015
会议地点Kuala Lumpur, Malaysia
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.
关键词Video-based Face Recognition Joint Space Learning Randomized Techniques
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11841
专题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],2015.
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
Joint Space Learning(470KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Cao Dong(曹冬)]的文章
[Ran He(赫然)]的文章
[Zhenan Sun]的文章
百度学术
百度学术中相似的文章
[Cao Dong(曹冬)]的文章
[Ran He(赫然)]的文章
[Zhenan Sun]的文章
必应学术
必应学术中相似的文章
[Cao Dong(曹冬)]的文章
[Ran He(赫然)]的文章
[Zhenan Sun]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Joint Space Learning for Video-based Face Recognition.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。