Child-centred motion-based age and gender estimation with neural network learning

Anara Sandygulova, Yerdaulet Absattar, Damir Doszhan, German I. Parisi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The focus of this work is to investigate how children's perception of the robot changes with age and gender, and to enable the robot to adapt to these differences for improving humanrobot interaction (HRI). We propose a neural network-based learning architecture to estimate children's age and gender based on the body motion performing a set of actions. To evaluate our system, we collected a fully annotated depth dataset of 28 children (aged between 7 and 16 years old) and applied it to a learning-based method for age and gender estimation by modeling children's 3D skeleton motion data. We discuss our results that show an average accuracy of 95.2% and 90.3% for age and gender respectively in the context of a real-world scenario.

Original languageEnglish
Title of host publicationWS-16-01
Subtitle of host publicationArtificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence
PublisherAI Access Foundation
Pages47-52
Number of pages6
VolumeWS-16-01 - WS-16-15
ISBN (Electronic)9781577357599
Publication statusPublished - Jan 1 2016
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: Feb 12 2016Feb 13 2016

Other

Other30th AAAI Conference on Artificial Intelligence, AAAI 2016
CountryUnited States
CityPhoenix
Period2/12/162/13/16

Fingerprint

Robots
Neural networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sandygulova, A., Absattar, Y., Doszhan, D., & Parisi, G. I. (2016). Child-centred motion-based age and gender estimation with neural network learning. In WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence (Vol. WS-16-01 - WS-16-15, pp. 47-52). AI Access Foundation.

Child-centred motion-based age and gender estimation with neural network learning. / Sandygulova, Anara; Absattar, Yerdaulet; Doszhan, Damir; Parisi, German I.

WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. Vol. WS-16-01 - WS-16-15 AI Access Foundation, 2016. p. 47-52.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sandygulova, A, Absattar, Y, Doszhan, D & Parisi, GI 2016, Child-centred motion-based age and gender estimation with neural network learning. in WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. vol. WS-16-01 - WS-16-15, AI Access Foundation, pp. 47-52, 30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix, United States, 2/12/16.
Sandygulova A, Absattar Y, Doszhan D, Parisi GI. Child-centred motion-based age and gender estimation with neural network learning. In WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. Vol. WS-16-01 - WS-16-15. AI Access Foundation. 2016. p. 47-52
Sandygulova, Anara ; Absattar, Yerdaulet ; Doszhan, Damir ; Parisi, German I. / Child-centred motion-based age and gender estimation with neural network learning. WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. Vol. WS-16-01 - WS-16-15 AI Access Foundation, 2016. pp. 47-52
@inproceedings{ce3af56c5cc14315955622de0d36427d,
title = "Child-centred motion-based age and gender estimation with neural network learning",
abstract = "The focus of this work is to investigate how children's perception of the robot changes with age and gender, and to enable the robot to adapt to these differences for improving humanrobot interaction (HRI). We propose a neural network-based learning architecture to estimate children's age and gender based on the body motion performing a set of actions. To evaluate our system, we collected a fully annotated depth dataset of 28 children (aged between 7 and 16 years old) and applied it to a learning-based method for age and gender estimation by modeling children's 3D skeleton motion data. We discuss our results that show an average accuracy of 95.2{\%} and 90.3{\%} for age and gender respectively in the context of a real-world scenario.",
author = "Anara Sandygulova and Yerdaulet Absattar and Damir Doszhan and Parisi, {German I.}",
year = "2016",
month = "1",
day = "1",
language = "English",
volume = "WS-16-01 - WS-16-15",
pages = "47--52",
booktitle = "WS-16-01",
publisher = "AI Access Foundation",
address = "United States",

}

TY - GEN

T1 - Child-centred motion-based age and gender estimation with neural network learning

AU - Sandygulova, Anara

AU - Absattar, Yerdaulet

AU - Doszhan, Damir

AU - Parisi, German I.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - The focus of this work is to investigate how children's perception of the robot changes with age and gender, and to enable the robot to adapt to these differences for improving humanrobot interaction (HRI). We propose a neural network-based learning architecture to estimate children's age and gender based on the body motion performing a set of actions. To evaluate our system, we collected a fully annotated depth dataset of 28 children (aged between 7 and 16 years old) and applied it to a learning-based method for age and gender estimation by modeling children's 3D skeleton motion data. We discuss our results that show an average accuracy of 95.2% and 90.3% for age and gender respectively in the context of a real-world scenario.

AB - The focus of this work is to investigate how children's perception of the robot changes with age and gender, and to enable the robot to adapt to these differences for improving humanrobot interaction (HRI). We propose a neural network-based learning architecture to estimate children's age and gender based on the body motion performing a set of actions. To evaluate our system, we collected a fully annotated depth dataset of 28 children (aged between 7 and 16 years old) and applied it to a learning-based method for age and gender estimation by modeling children's 3D skeleton motion data. We discuss our results that show an average accuracy of 95.2% and 90.3% for age and gender respectively in the context of a real-world scenario.

UR - http://www.scopus.com/inward/record.url?scp=85022024668&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022024668&partnerID=8YFLogxK

M3 - Conference contribution

VL - WS-16-01 - WS-16-15

SP - 47

EP - 52

BT - WS-16-01

PB - AI Access Foundation

ER -