Computer Vision for Head Pose Estimation: Review of a Competition

Heikki Huttunen; Ke Chen; Abhishek Thakur; Artus Krohn-Grimberghe; Oguzhan Gencoglu; Xingyang Ni; Mohammed Al-Musawi; Lei Xu; Hendrik Jacob van Veen

doi:10.1007/978-3-319-19665-7_6

Computer Vision for Head Pose Estimation: Review of a Competition

Heikki Huttunen, Ke Chen, Abhishek Thakur, Artus Krohn-Grimberghe, Oguzhan Gencoglu, Xingyang Ni, Mohammed Al-Musawi, Lei Xu, Hendrik Jacob van Veen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

8 Citations (Scopus)

Abstract

This paper studies the prediction of head pose from still images, and summarizes the outcome of a recently organized competition, where the task was to predict the yaw and pitch angles of an image dataset with 2790 samples with known angles. The competition received 292 entries from 52 participants, the best ones clearly exceeding the state-of-the-art accuracy. In this paper, we present the key methodologies behind selected top methods, summarize their prediction accuracy and compare with the current state of the art.

Original language	English
Title of host publication	19th Scandinavian Conference on Image Analysis (SCIA)
Publisher	Springer International Publishing
Pages	65-75
Number of pages	10
Volume	9127
ISBN (Electronic)	978-3-319-19665-7
ISBN (Print)	978-3-319-19664-0
DOIs	https://doi.org/10.1007/978-3-319-19665-7_6
Publication status	Published - 9 Jun 2015
Publication type	A4 Article in conference proceedings
Event	Scandinavian Conference on Image Analysis - Duration: 1 Jan 1900 → …

Conference

Conference	Scandinavian Conference on Image Analysis
Period	1/01/00 → …

Keywords

Machine learning

Publication forum classification

Publication forum level 1

Access to Document

10.1007/978-3-319-19665-7_6

Cite this

@inproceedings{403fc72526904d3eb20e45bd0a7edb91,

title = "Computer Vision for Head Pose Estimation: Review of a Competition",

abstract = "This paper studies the prediction of head pose from still images, and summarizes the outcome of a recently organized competition, where the task was to predict the yaw and pitch angles of an image dataset with 2790 samples with known angles. The competition received 292 entries from 52 participants, the best ones clearly exceeding the state-of-the-art accuracy. In this paper, we present the key methodologies behind selected top methods, summarize their prediction accuracy and compare with the current state of the art.",

keywords = "Machine learning",

author = "Heikki Huttunen and Ke Chen and Abhishek Thakur and Artus Krohn-Grimberghe and Oguzhan Gencoglu and Xingyang Ni and Mohammed Al-Musawi and Lei Xu and {van Veen}, {Hendrik Jacob}",

note = "AUX=sgn,{"}Ni, Xingyang{"} AUX=sgn,{"}Al-Musawi, Mohammed{"} AUX=sgn,{"}Xu, Lei{"}; Scandinavian Conference on Image Analysis ; Conference date: 01-01-1900",

year = "2015",

month = jun,

day = "9",

doi = "10.1007/978-3-319-19665-7_6",

language = "English",

isbn = "978-3-319-19664-0",

volume = "9127",

pages = "65--75",

booktitle = "19th Scandinavian Conference on Image Analysis (SCIA)",

publisher = "Springer International Publishing",

}

Huttunen, H, Chen, K, Thakur, A, Krohn-Grimberghe, A, Gencoglu, O, Ni, X, Al-Musawi, M, Xu, L & van Veen, HJ 2015, Computer Vision for Head Pose Estimation: Review of a Competition. in 19th Scandinavian Conference on Image Analysis (SCIA). vol. 9127, Springer International Publishing, pp. 65-75, Scandinavian Conference on Image Analysis, 1/01/00. https://doi.org/10.1007/978-3-319-19665-7_6

TY - GEN

T1 - Computer Vision for Head Pose Estimation: Review of a Competition

AU - Huttunen, Heikki

AU - Chen, Ke

AU - Thakur, Abhishek

AU - Krohn-Grimberghe, Artus

AU - Gencoglu, Oguzhan

AU - Ni, Xingyang

AU - Al-Musawi, Mohammed

AU - Xu, Lei

AU - van Veen, Hendrik Jacob

N1 - AUX=sgn,"Ni, Xingyang" AUX=sgn,"Al-Musawi, Mohammed" AUX=sgn,"Xu, Lei"

PY - 2015/6/9

Y1 - 2015/6/9

N2 - This paper studies the prediction of head pose from still images, and summarizes the outcome of a recently organized competition, where the task was to predict the yaw and pitch angles of an image dataset with 2790 samples with known angles. The competition received 292 entries from 52 participants, the best ones clearly exceeding the state-of-the-art accuracy. In this paper, we present the key methodologies behind selected top methods, summarize their prediction accuracy and compare with the current state of the art.

AB - This paper studies the prediction of head pose from still images, and summarizes the outcome of a recently organized competition, where the task was to predict the yaw and pitch angles of an image dataset with 2790 samples with known angles. The competition received 292 entries from 52 participants, the best ones clearly exceeding the state-of-the-art accuracy. In this paper, we present the key methodologies behind selected top methods, summarize their prediction accuracy and compare with the current state of the art.

KW - Machine learning

U2 - 10.1007/978-3-319-19665-7_6

DO - 10.1007/978-3-319-19665-7_6

M3 - Conference contribution

SN - 978-3-319-19664-0

VL - 9127

SP - 65

EP - 75

BT - 19th Scandinavian Conference on Image Analysis (SCIA)

PB - Springer International Publishing

T2 - Scandinavian Conference on Image Analysis

Y2 - 1 January 1900

ER -

Computer Vision for Head Pose Estimation: Review of a Competition

Abstract

Conference

Keywords

Publication forum classification

Access to Document

Fingerprint

Cite this