Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database

Eirikur Agustsson; Radu Timofte; Sergio Escalera; Xavier Baro; Isabelle Guyon; Rasmus Rothe

doi:10.1109/FG.2017.20

Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database

Eirikur Agustsson, Radu Timofte, Sergio Escalera, Xavier Baro, Isabelle Guyon, Rasmus Rothe

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

69 Citationer (Scopus)

Abstract

After decades of research, the real (biological) age estimation from a single face image reached maturity thanks to the availability of large public face databases and impressive accuracies achieved by recently proposed methods. The estimation of 'apparent age' is a related task concerning the age perceived by human observers. Significant advances have been also made in this new research direction with the recent Looking At People challenges. In this paper we make several contributions to age estimation research. (i) We introduce APPA-REAL, a large face image database with both real and apparent age annotations. (ii)We study the relationship between real and apparent age. (iii) We develop a residual age regression method to further improve the performance. (iv) We show that real age estimation can be successfully tackled as an apparent age estimation followed by an apparent to real age residual regression. (v) We graphically reveal the facial regions on which the CNN focuses in order to perform apparent and real age estimation tasks.

Originalsprog	Engelsk
Titel	Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017
Antal sider	8
Forlag	IEEE Signal Processing Society
Publikationsdato	28 jun. 2017
Sider	87-94
Artikelnummer	7961727
ISBN (Elektronisk)	9781509040230
DOI	https://doi.org/10.1109/FG.2017.20
Status	Udgivet - 28 jun. 2017
Begivenhed	12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - Washington, USA Varighed: 30 maj 2017 → 3 jun. 2017

Konference

Konference	12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017
Land/Område	USA
By	Washington
Periode	30/05/2017 → 03/06/2017
Sponsor	3dMD, Baidu, DI4D, et al., Mitsubishi Electric Research Laboratories, Inc, NSF

Navn

Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017

Bibliografisk note

Publisher Copyright:
© 2017 IEEE.

Adgang til dokumentet

10.1109/FG.2017.20

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

Link to publication in Scopus

Citationsformater

Agustsson, E., Timofte, R., Escalera, S., Baro, X., Guyon, I., & Rothe, R. (2017). Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database. I Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017 (s. 87-94). Artikel 7961727 IEEE Signal Processing Society. https://doi.org/10.1109/FG.2017.20

Agustsson, Eirikur ; Timofte, Radu ; Escalera, Sergio et al. / Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database. Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017. IEEE Signal Processing Society, 2017. s. 87-94 (Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017).

@inproceedings{498d9e7dd805436fac264817936f43d6,

title = "Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database",

abstract = "After decades of research, the real (biological) age estimation from a single face image reached maturity thanks to the availability of large public face databases and impressive accuracies achieved by recently proposed methods. The estimation of 'apparent age' is a related task concerning the age perceived by human observers. Significant advances have been also made in this new research direction with the recent Looking At People challenges. In this paper we make several contributions to age estimation research. (i) We introduce APPA-REAL, a large face image database with both real and apparent age annotations. (ii)We study the relationship between real and apparent age. (iii) We develop a residual age regression method to further improve the performance. (iv) We show that real age estimation can be successfully tackled as an apparent age estimation followed by an apparent to real age residual regression. (v) We graphically reveal the facial regions on which the CNN focuses in order to perform apparent and real age estimation tasks.",

author = "Eirikur Agustsson and Radu Timofte and Sergio Escalera and Xavier Baro and Isabelle Guyon and Rasmus Rothe",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 ; Conference date: 30-05-2017 Through 03-06-2017",

year = "2017",

month = jun,

day = "28",

doi = "10.1109/FG.2017.20",

language = "English",

series = "Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017",

pages = "87--94",

booktitle = "Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017",

publisher = "IEEE Signal Processing Society",

address = "United States",

}

Agustsson, E, Timofte, R, Escalera, S, Baro, X, Guyon, I & Rothe, R 2017, Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database. i Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017., 7961727, IEEE Signal Processing Society, Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017, s. 87-94, 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017, Washington, USA, 30/05/2017. https://doi.org/10.1109/FG.2017.20

Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database. / Agustsson, Eirikur; Timofte, Radu; Escalera, Sergio et al.
Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017. IEEE Signal Processing Society, 2017. s. 87-94 7961727 (Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database

AU - Agustsson, Eirikur

AU - Timofte, Radu

AU - Escalera, Sergio

AU - Baro, Xavier

AU - Guyon, Isabelle

AU - Rothe, Rasmus

PY - 2017/6/28

Y1 - 2017/6/28

N2 - After decades of research, the real (biological) age estimation from a single face image reached maturity thanks to the availability of large public face databases and impressive accuracies achieved by recently proposed methods. The estimation of 'apparent age' is a related task concerning the age perceived by human observers. Significant advances have been also made in this new research direction with the recent Looking At People challenges. In this paper we make several contributions to age estimation research. (i) We introduce APPA-REAL, a large face image database with both real and apparent age annotations. (ii)We study the relationship between real and apparent age. (iii) We develop a residual age regression method to further improve the performance. (iv) We show that real age estimation can be successfully tackled as an apparent age estimation followed by an apparent to real age residual regression. (v) We graphically reveal the facial regions on which the CNN focuses in order to perform apparent and real age estimation tasks.

AB - After decades of research, the real (biological) age estimation from a single face image reached maturity thanks to the availability of large public face databases and impressive accuracies achieved by recently proposed methods. The estimation of 'apparent age' is a related task concerning the age perceived by human observers. Significant advances have been also made in this new research direction with the recent Looking At People challenges. In this paper we make several contributions to age estimation research. (i) We introduce APPA-REAL, a large face image database with both real and apparent age annotations. (ii)We study the relationship between real and apparent age. (iii) We develop a residual age regression method to further improve the performance. (iv) We show that real age estimation can be successfully tackled as an apparent age estimation followed by an apparent to real age residual regression. (v) We graphically reveal the facial regions on which the CNN focuses in order to perform apparent and real age estimation tasks.

UR - http://www.scopus.com/inward/record.url?scp=85026324900&partnerID=8YFLogxK

U2 - 10.1109/FG.2017.20

DO - 10.1109/FG.2017.20

M3 - Article in proceeding

AN - SCOPUS:85026324900

T3 - Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017

SP - 87

EP - 94

BT - Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017

PB - IEEE Signal Processing Society

T2 - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017

Y2 - 30 May 2017 through 3 June 2017

ER -

Agustsson E, Timofte R, Escalera S, Baro X, Guyon I, Rothe R. Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database. I Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017. IEEE Signal Processing Society. 2017. s. 87-94. 7961727. (Proceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017). doi: 10.1109/FG.2017.20

Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database

Abstract

Konference

Bibliografisk note

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Citationsformater