Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/98388
Title: | Neighborhood repulsed metric learning for kinship verification | Authors: | Lu, Jiwen Hu, Junlin Zhou, Xiuzhuang Shang, Yuanyuan Tan, Yap Peng Wang, Gang |
Keywords: | DRNTU::Engineering::Electrical and electronic engineering | Issue Date: | 2012 | Source: | Lu, J., Hu, J., Zhou, X., Shang, Y., Tan, Y. P., Wang, G., et al. (2012). Neighborhood repulsed metric learning for kinship verification. 2012 IEEE Conference on Computer Vision and Pattern Recognition. | Conference: | IEEE Conference on Computer Vision and Pattern Recognition (2012 : Providence, Rhode Island, US) | Abstract: | Kinship verification from facial images is a challenging problem in computer vision, and there is a very few attempts on tackling this problem in the literature. In this paper, we propose a new neighborhood repulsed metric learning (NRML) method for kinship verification. Motivated by the fact that interclass samples (without kinship relations) with higher similarity usually lie in a neighborhood and are more easily misclassified than those with lower similarity, we aim to learn a distance metric under which the intraclass samples (with kinship relations) are pushed as close as possible and interclass samples lying in a neighborhood are repulsed and pulled as far as possible, simultaneously, such that more discriminative information can be exploited for verification. Moreover, we propose a multiview NRM-L (MNRML) method to seek a common distance metric to make better use of multiple feature descriptors to further improve the verification performance. Experimental results are presented to demonstrate the efficacy of the proposed methods. | URI: | https://hdl.handle.net/10356/98388 http://hdl.handle.net/10220/12489 |
DOI: | 10.1109/CVPR.2012.6247978 | Schools: | School of Electrical and Electronic Engineering | Rights: | © 2012 IEEE. | Fulltext Permission: | none | Fulltext Availability: | No Fulltext |
Appears in Collections: | EEE Conference Papers |
SCOPUSTM
Citations
5
75
Updated on Mar 12, 2024
Page view(s) 5
910
Updated on Mar 15, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.