2014
DOI: 10.1109/tifs.2014.2327757
|View full text |Cite
|
Sign up to set email alerts
|

Discriminative Multimetric Learning for Kinship Verification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
90
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 200 publications
(90 citation statements)
references
References 30 publications
0
90
0
Order By: Relevance
“…Following the dramatic improvements in deep learning, recent studies have started to utilize deep architectures such as gated autoencoders [7], stacked autoencoders [30], convolutional neural networks (CNN) [37,21], and convolutional Siamese networks [17] for modeling kinship patterns. Metric learning has also been adopted for both engineered [20,15,35,34] and deep learned features [30,17].…”
Section: Related Workmentioning
confidence: 99%
“…Following the dramatic improvements in deep learning, recent studies have started to utilize deep architectures such as gated autoencoders [7], stacked autoencoders [30], convolutional neural networks (CNN) [37,21], and convolutional Siamese networks [17] for modeling kinship patterns. Metric learning has also been adopted for both engineered [20,15,35,34] and deep learned features [30,17].…”
Section: Related Workmentioning
confidence: 99%
“…The KinFaceW-I [3], KinFaceW-II [3] and TSKinFace [11] datasets are chosen as the target domain. What their indifferences are: they consist of public figures or celebrities and their parents or their child from the internet, and have four kinds of kinrelation such as Father-Son (FS), Father-Daughter (FD), Mother-Son (MS), and Mother-Daughter (MD), and all images have aligned with 64*64 pixels (see Fig.3).…”
Section: Datasets and Preprocessingmentioning
confidence: 99%
“…However, it could not be directly used to judge kinship relation in the practical application because of the privacy, money, time and cooperation. Since Fang et al [1] firstly proposed to solve the task of kinship verification from facial images by computer vision technology, more and more research communities have paid attention on it [2][3][4][5][6]. Kinship verification could be used in mining the human social relation, finding missing children and improving face recognition.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Since 2010, great efforts have been put towards advancing automatic kinship recognition capabilities [84,85,86,87,88,89,90,91,92,93,94,95,96]. The recent works resulted from the release of KinWild I-II, which was first introduced as part of a FG 2015 challenge [89].…”
Section: Kinship Verificationmentioning
confidence: 99%