TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Facial Age Estimation Using Robust Label Distribution

Tutkimustuotosvertaisarvioitu

Standard

Facial Age Estimation Using Robust Label Distribution. / Chen, Ke; Kämäräinen, Joni-Kristian; Zhang, Zhaoxiang.

MM '16 Proceedings of the 2016 ACM on Multimedia Conference. ACM, 2016. s. 77-81.

Tutkimustuotosvertaisarvioitu

Harvard

Chen, K, Kämäräinen, J-K & Zhang, Z 2016, Facial Age Estimation Using Robust Label Distribution. julkaisussa MM '16 Proceedings of the 2016 ACM on Multimedia Conference. ACM, Sivut 77-81, ACM MULTIMEDIA CONFERENCE, 1/01/00. https://doi.org/10.1145/2964284.2967186

APA

Chen, K., Kämäräinen, J-K., & Zhang, Z. (2016). Facial Age Estimation Using Robust Label Distribution. teoksessa MM '16 Proceedings of the 2016 ACM on Multimedia Conference (Sivut 77-81). ACM. https://doi.org/10.1145/2964284.2967186

Vancouver

Chen K, Kämäräinen J-K, Zhang Z. Facial Age Estimation Using Robust Label Distribution. julkaisussa MM '16 Proceedings of the 2016 ACM on Multimedia Conference. ACM. 2016. s. 77-81 https://doi.org/10.1145/2964284.2967186

Author

Chen, Ke ; Kämäräinen, Joni-Kristian ; Zhang, Zhaoxiang. / Facial Age Estimation Using Robust Label Distribution. MM '16 Proceedings of the 2016 ACM on Multimedia Conference. ACM, 2016. Sivut 77-81

Bibtex - Lataa

@inproceedings{487da5ba60b044fa87f9c713bf408e1a,
title = "Facial Age Estimation Using Robust Label Distribution",
abstract = "Facial age estimation, to predict the persons' exact ages given facial images, usually encounters the data sparsity problem due to the difficulties in data annotation. To mitigate the suffering from sparse data, a recent label distribution learning (LDL) algorithm attempts to embed label correlation into a classification based framework. However, the conventional label distribution learning framework only considers correlations across the neighbouring variables (ages), which omits the intrinsic complexity of age classes during different ageing periods (age groups). In the light of this, we introduce a novel concept of robust label distribution for scalar-valued labels, which is designed to encode the age scalars into label distribution matrices, i.e. two-dimensional Gaussian distributions along age classes and age groups respectively. Overcoming the limitations of conventional hard group boundaries in age grouping and capturing intrinsic inter-group dependency, our framework achieves robust and competitive performance over the conventional algorithms on two popular benchmarks for human age estimation.",
author = "Ke Chen and Joni-Kristian K{\"a}m{\"a}r{\"a}inen and Zhaoxiang Zhang",
year = "2016",
doi = "10.1145/2964284.2967186",
language = "English",
pages = "77--81",
booktitle = "MM '16 Proceedings of the 2016 ACM on Multimedia Conference",
publisher = "ACM",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Facial Age Estimation Using Robust Label Distribution

AU - Chen, Ke

AU - Kämäräinen, Joni-Kristian

AU - Zhang, Zhaoxiang

PY - 2016

Y1 - 2016

N2 - Facial age estimation, to predict the persons' exact ages given facial images, usually encounters the data sparsity problem due to the difficulties in data annotation. To mitigate the suffering from sparse data, a recent label distribution learning (LDL) algorithm attempts to embed label correlation into a classification based framework. However, the conventional label distribution learning framework only considers correlations across the neighbouring variables (ages), which omits the intrinsic complexity of age classes during different ageing periods (age groups). In the light of this, we introduce a novel concept of robust label distribution for scalar-valued labels, which is designed to encode the age scalars into label distribution matrices, i.e. two-dimensional Gaussian distributions along age classes and age groups respectively. Overcoming the limitations of conventional hard group boundaries in age grouping and capturing intrinsic inter-group dependency, our framework achieves robust and competitive performance over the conventional algorithms on two popular benchmarks for human age estimation.

AB - Facial age estimation, to predict the persons' exact ages given facial images, usually encounters the data sparsity problem due to the difficulties in data annotation. To mitigate the suffering from sparse data, a recent label distribution learning (LDL) algorithm attempts to embed label correlation into a classification based framework. However, the conventional label distribution learning framework only considers correlations across the neighbouring variables (ages), which omits the intrinsic complexity of age classes during different ageing periods (age groups). In the light of this, we introduce a novel concept of robust label distribution for scalar-valued labels, which is designed to encode the age scalars into label distribution matrices, i.e. two-dimensional Gaussian distributions along age classes and age groups respectively. Overcoming the limitations of conventional hard group boundaries in age grouping and capturing intrinsic inter-group dependency, our framework achieves robust and competitive performance over the conventional algorithms on two popular benchmarks for human age estimation.

U2 - 10.1145/2964284.2967186

DO - 10.1145/2964284.2967186

M3 - Conference contribution

SP - 77

EP - 81

BT - MM '16 Proceedings of the 2016 ACM on Multimedia Conference

PB - ACM

ER -