Learning to pool high-level features for face representation

Learning to pool high-level features for face representation
复制标题

学习汇集高级特征以进行人脸表示

DOI:
10.1007/s00371-014-1049-8
复制
发表时间:
2015-12
期刊:
影响因子:
3.5
通讯作者:
Dou Yumin
Dou Yumin
中科院分区:
计算机科学3区
文献类型:
--
作者:
Huang Renjie;Ye Mao;Xu Pei;Li Tao;Dou Yumin

文献摘要

参考文献

被引文献

相似文献

可用的脸部描述符总是通过手工设计的汇集方案或无需汇集过程来生成。我们建议学习高级特征的汇集方案。首先,对人脸图像的密集采样点进行局部特征提取。然后,使用加权和合并来获得该人脸图像块的高层特征。通过学习汇聚权值,将局部特征的结构信息融合到块的高层特征中。同时,学习了一种线性变换来降低该高级特征的维度。我们的主要贡献是提出了一种能够捕捉块中局部特征之间的结构信息的池化方法。这种结构信息包括面部结构和轮廓。在多个人脸数据集上的实验验证了该方法的有效性。
The available face descriptors are always generated by a hand-designed pooling scheme or without a pooling process. We propose to learn a pooling scheme for high-level features. First, we obtain the local features on the densely sampled points on a face image. Then, a weighted-sum pooling is used to obtain the high-level feature of a block of this face image. By learning the pooling weights, the structure information of local features is integrated into the high-level feature of the block. At the same time, a linear transformation is learned to reduce the dimension of this high-level feature. Our main contribution is the method of learning the pooling scheme, which can capture the structure information between the local features in a block. This structure information includes the facial structures and contours. The experiments on multiple face datasets confirm the efficiency and effectiveness of our method.
DOI: 10.1198/jasa.2003.s308
发表时间: 2003-12
影响因子: 3.7
作者:
M. Timmerman
通讯作者: M. Timmerman
DOI: 10.1002/wics.101
发表时间: 2010-07-01
影响因子: 3.2
作者:
Abdi, Herve;Williams, Lynne J.
通讯作者: Williams, Lynne J.
DOI: 10.1109/fg.2011.5771389
发表时间: 2011-03
期刊: Face and Gesture 2011
影响因子: --
作者:
Zhen Cui;S. Shan;Xilin Chen;Lei Zhang
通讯作者: Zhen Cui;S. Shan;Xilin Chen;Lei Zhang
DOI: 10.1007/978-3-540-75690-3_13
发表时间: 2007-10
影响因子: 10.6
作者:
Xiaoyang Tan;B. Triggs
通讯作者: Xiaoyang Tan;B. Triggs
DOI: 10.1109/cvpr.2013.456
发表时间: 2013-06
期刊: 2013 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Zhen Cui;Wen Li;Dong Xu;S. Shan;Xilin Chen
通讯作者: Zhen Cui;Wen Li;Dong Xu;S. Shan;Xilin Chen