Tampere University of Technology

TUTCRIS Research Portal

Cumulative Attribute Space Regression for Head Pose Estimation and Color Constancy

Research output: Contribution to journalArticleScientificpeer-review

Standard

Cumulative Attribute Space Regression for Head Pose Estimation and Color Constancy. / Chen, Ke; Jia, Kui; Huttunen, Heikki; Matas, Jiri; Kämäräinen, Joni.

In: Pattern Recognition, Vol. 87, 03.2019, p. 29-37.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Bibtex - Download

@article{f220d0cc4f674aab8b24995cdef4ae5a,
title = "Cumulative Attribute Space Regression for Head Pose Estimation and Color Constancy",
abstract = "Two-stage Cumulative Attribute (CA) regression has been found effective in regression problems of computer vision such as facial age and crowd density estimation. The first stage regression maps input features to cumulative attributes that encode correlations between target values. The previous works have dealt with single output regression. In this work, we propose cumulative attribute spaces for 2- and 3-output (multivariate) regression. We show how the original CA space can be generalized to multiple output by the Cartesian product (CartCA). However, for target spaces with more than two outputs the CartCA becomes computationally infeasible and therefore we propose an approximate solution - multi-view CA (MvCA) - where CartCA is applied to output pairs. We experimentally verify improved performance of the CartCA and MvCA spaces in 2D and 3D face pose estimation and three-output (RGB) illuminant estimation for color constancy.",
author = "Ke Chen and Kui Jia and Heikki Huttunen and Jiri Matas and Joni K{\"a}m{\"a}r{\"a}inen",
year = "2019",
month = "3",
doi = "10.1016/j.patcog.2018.10.015",
language = "English",
volume = "87",
pages = "29--37",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "ELSEVIER SCI LTD",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Cumulative Attribute Space Regression for Head Pose Estimation and Color Constancy

AU - Chen, Ke

AU - Jia, Kui

AU - Huttunen, Heikki

AU - Matas, Jiri

AU - Kämäräinen, Joni

PY - 2019/3

Y1 - 2019/3

N2 - Two-stage Cumulative Attribute (CA) regression has been found effective in regression problems of computer vision such as facial age and crowd density estimation. The first stage regression maps input features to cumulative attributes that encode correlations between target values. The previous works have dealt with single output regression. In this work, we propose cumulative attribute spaces for 2- and 3-output (multivariate) regression. We show how the original CA space can be generalized to multiple output by the Cartesian product (CartCA). However, for target spaces with more than two outputs the CartCA becomes computationally infeasible and therefore we propose an approximate solution - multi-view CA (MvCA) - where CartCA is applied to output pairs. We experimentally verify improved performance of the CartCA and MvCA spaces in 2D and 3D face pose estimation and three-output (RGB) illuminant estimation for color constancy.

AB - Two-stage Cumulative Attribute (CA) regression has been found effective in regression problems of computer vision such as facial age and crowd density estimation. The first stage regression maps input features to cumulative attributes that encode correlations between target values. The previous works have dealt with single output regression. In this work, we propose cumulative attribute spaces for 2- and 3-output (multivariate) regression. We show how the original CA space can be generalized to multiple output by the Cartesian product (CartCA). However, for target spaces with more than two outputs the CartCA becomes computationally infeasible and therefore we propose an approximate solution - multi-view CA (MvCA) - where CartCA is applied to output pairs. We experimentally verify improved performance of the CartCA and MvCA spaces in 2D and 3D face pose estimation and three-output (RGB) illuminant estimation for color constancy.

U2 - 10.1016/j.patcog.2018.10.015

DO - 10.1016/j.patcog.2018.10.015

M3 - Article

VL - 87

SP - 29

EP - 37

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -