Face recognition based on recurrent regression neural network

Face recognition based on recurrent regression neural network
复制标题

基于递归回归神经网络的人脸识别

DOI:
10.1016/j.neucom.2018.02.037
复制
发表时间:
2018-07
期刊:
影响因子:
6
通讯作者:
Zhang Tong
Zhang Tong
中科院分区:
计算机科学2区
文献类型:
--
作者:
Li Yang;Zheng Wenming;Cui Zhen;Zhang Tong

文献摘要

参考文献

被引文献

相似文献

为了解决图像的顺序变化,包括姿势,在本文中,我们提出了一个递归回归神经网络(RRNN)框架,以统一两个经典的任务,跨姿势人脸识别的静态图像和视频。为了模拟图像的变化,我们显式地构造序列图像的潜在依赖关系,从而正则化最终的学习模型。通过对顺序相邻的图像进行渐进变换,RRNN可以自适应地记忆和忘记有利于最终分类的信息。对于静止图像的人脸识别,给定任意一幅具有任意一个姿态的图像,我们递归地预测具有其序列姿态的图像,期望捕获其他姿态的一些有用信息。对于基于视频的人脸识别,递归回归需要一个完整的序列,而不是一个图像作为其输入。我们在静态人脸图像数据集MultiPIE和人脸视频数据集YouTube Celebration(YTC)上验证了RRNN。综合实验结果证明了所提出的RRNN方法的有效性。
To address the sequential changes of images including poses, in this paper we propose a recurrent regression neural network (RRNN) framework to unify two classic tasks of cross-pose face recognition on still images and videos. To imitate the changes of images, we explicitly construct the potential dependencies of sequential images so as to regularizing the final learning model. By performing progressive transforms for sequentially adjacent images, RRNN can adaptively memorize and forget the information that benefits for the final classification. For face recognition of still images, given any one image with any one pose, we recurrently predict the images with its sequential poses to expect to capture some useful information of other poses. For video-based face recognition, the recurrent regression takes one entire sequence rather than one image as its input. We verify RRNN in still face image dataset MultiPIE and face video dataset YouTube Celebrities (YTC). The comprehensive experimental results demonstrate the effectiveness of the proposed RRNN method.
DOI: 10.1109/tip.2017.2746993
发表时间: 2015-06
期刊: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Ruiping Wang;Zhiwu Huang;S. Shan;Xilin Chen
通讯作者: Ruiping Wang;Zhiwu Huang;S. Shan;Xilin Chen
DOI: 10.1109/cvpr.2015.7298717
发表时间: 2015-06
期刊: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Jiwen Lu;G. Wang;Weihong Deng;P. Moulin;Jie Zhou
通讯作者: Jiwen Lu;G. Wang;Weihong Deng;P. Moulin;Jie Zhou
学习用于人脸识别的堆叠图像描述符
DOI: 10.1109/tcsvt.2015.2473415
发表时间: 2016-09
期刊: IEEE Transaction on Circuits and Systems for Video Technology
影响因子: --
作者:
Zhen Lei;Dong Yi;Stan Z. Li
通讯作者: Stan Z. Li
DOI: 10.1109/tmm.2010.2087320
发表时间: 2011-02
影响因子: 7.3
作者:
J. Choi;W. D. Neve;K. Plataniotis;Yong Man Ro
通讯作者: J. Choi;W. D. Neve;K. Plataniotis;Yong Man Ro
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