Affective gait recognition and baseline evaluation from real world samples

Vili Kellokumpu (Corresponding author), Markus Särkiniemi, Guoying Zhao

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

1 Citation (Scopus)

Abstract

Over the years a lot of research efforts have been put into recognizing human emotions from facial expressions. However, in many scenarios access to suitable face data is difficult, and therefore there is a need for methodology that can be used when people are observed from a distance. A potential modality for this is human gait. Early attempts to recognize human emotion from gait have been limited to acted data. Furthermore, in these approaches the data has been captured in controlled settings. This paper presents the first experiments for automated affective gait recognition using non acted real world samples. A database of 96 subjects affected by positive or negative feedback is collected and two baseline methods are used to recognize the affective state of a person. The baseline results are promising and encourage further study in this domain.

Original languageEnglish
Title of host publicationComputer Vision - ACCV 2016 Workshops
Subtitle of host publicationACCV 2016 International Workshops
EditorsJiwen Lu, Kai-Kuang Ma, Chu-Song Chen
PublisherSpringer
Pages567-575
Number of pages9
ISBN (Electronic)978-3-319-54407-6
ISBN (Print)978-3-319-54406-9
DOIs
Publication statusPublished - 1 Jan 2017
MoE publication typeA4 Article in a conference publication
Event13th Asian Conference on Computer Vision, ACCV 2016 - Taipei, Taiwan, Province of China
Duration: 20 Nov 201624 Nov 2016

Publication series

SeriesLecture Notes in Computer Science
Volume10116
ISSN0302-9743

Conference

Conference13th Asian Conference on Computer Vision, ACCV 2016
CountryTaiwan, Province of China
City Taipei
Period20/11/1624/11/16

Fingerprint

Gait Recognition
Baseline
Gait
Feedback
Evaluation
Positive Feedback
Negative Feedback
Facial Expression
Modality
Person
Face
Scenarios
Methodology
Experiments
Experiment
Human
Emotion

Cite this

Kellokumpu, V., Särkiniemi, M., & Zhao, G. (2017). Affective gait recognition and baseline evaluation from real world samples. In J. Lu, K-K. Ma, & C-S. Chen (Eds.), Computer Vision - ACCV 2016 Workshops: ACCV 2016 International Workshops (pp. 567-575). Springer. Lecture Notes in Computer Science, Vol.. 10116 https://doi.org/10.1007/978-3-319-54407-6_38
Kellokumpu, Vili ; Särkiniemi, Markus ; Zhao, Guoying. / Affective gait recognition and baseline evaluation from real world samples. Computer Vision - ACCV 2016 Workshops: ACCV 2016 International Workshops. editor / Jiwen Lu ; Kai-Kuang Ma ; Chu-Song Chen. Springer, 2017. pp. 567-575 (Lecture Notes in Computer Science, Vol. 10116).
@inproceedings{e46e5123585f439ca05470b7f867fb49,
title = "Affective gait recognition and baseline evaluation from real world samples",
abstract = "Over the years a lot of research efforts have been put into recognizing human emotions from facial expressions. However, in many scenarios access to suitable face data is difficult, and therefore there is a need for methodology that can be used when people are observed from a distance. A potential modality for this is human gait. Early attempts to recognize human emotion from gait have been limited to acted data. Furthermore, in these approaches the data has been captured in controlled settings. This paper presents the first experiments for automated affective gait recognition using non acted real world samples. A database of 96 subjects affected by positive or negative feedback is collected and two baseline methods are used to recognize the affective state of a person. The baseline results are promising and encourage further study in this domain.",
author = "Vili Kellokumpu and Markus S{\"a}rkiniemi and Guoying Zhao",
year = "2017",
month = "1",
day = "1",
doi = "10.1007/978-3-319-54407-6_38",
language = "English",
isbn = "978-3-319-54406-9",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "567--575",
editor = "Jiwen Lu and Kai-Kuang Ma and Chu-Song Chen",
booktitle = "Computer Vision - ACCV 2016 Workshops",
address = "Germany",

}

Kellokumpu, V, Särkiniemi, M & Zhao, G 2017, Affective gait recognition and baseline evaluation from real world samples. in J Lu, K-K Ma & C-S Chen (eds), Computer Vision - ACCV 2016 Workshops: ACCV 2016 International Workshops. Springer, Lecture Notes in Computer Science, vol. 10116, pp. 567-575, 13th Asian Conference on Computer Vision, ACCV 2016, Taipei, Taiwan, Province of China, 20/11/16. https://doi.org/10.1007/978-3-319-54407-6_38

Affective gait recognition and baseline evaluation from real world samples. / Kellokumpu, Vili (Corresponding author); Särkiniemi, Markus; Zhao, Guoying.

Computer Vision - ACCV 2016 Workshops: ACCV 2016 International Workshops. ed. / Jiwen Lu; Kai-Kuang Ma; Chu-Song Chen. Springer, 2017. p. 567-575 (Lecture Notes in Computer Science, Vol. 10116).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Affective gait recognition and baseline evaluation from real world samples

AU - Kellokumpu, Vili

AU - Särkiniemi, Markus

AU - Zhao, Guoying

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Over the years a lot of research efforts have been put into recognizing human emotions from facial expressions. However, in many scenarios access to suitable face data is difficult, and therefore there is a need for methodology that can be used when people are observed from a distance. A potential modality for this is human gait. Early attempts to recognize human emotion from gait have been limited to acted data. Furthermore, in these approaches the data has been captured in controlled settings. This paper presents the first experiments for automated affective gait recognition using non acted real world samples. A database of 96 subjects affected by positive or negative feedback is collected and two baseline methods are used to recognize the affective state of a person. The baseline results are promising and encourage further study in this domain.

AB - Over the years a lot of research efforts have been put into recognizing human emotions from facial expressions. However, in many scenarios access to suitable face data is difficult, and therefore there is a need for methodology that can be used when people are observed from a distance. A potential modality for this is human gait. Early attempts to recognize human emotion from gait have been limited to acted data. Furthermore, in these approaches the data has been captured in controlled settings. This paper presents the first experiments for automated affective gait recognition using non acted real world samples. A database of 96 subjects affected by positive or negative feedback is collected and two baseline methods are used to recognize the affective state of a person. The baseline results are promising and encourage further study in this domain.

UR - http://www.scopus.com/inward/record.url?scp=85016174234&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-54407-6_38

DO - 10.1007/978-3-319-54407-6_38

M3 - Conference article in proceedings

AN - SCOPUS:85016174234

SN - 978-3-319-54406-9

T3 - Lecture Notes in Computer Science

SP - 567

EP - 575

BT - Computer Vision - ACCV 2016 Workshops

A2 - Lu, Jiwen

A2 - Ma, Kai-Kuang

A2 - Chen, Chu-Song

PB - Springer

ER -

Kellokumpu V, Särkiniemi M, Zhao G. Affective gait recognition and baseline evaluation from real world samples. In Lu J, Ma K-K, Chen C-S, editors, Computer Vision - ACCV 2016 Workshops: ACCV 2016 International Workshops. Springer. 2017. p. 567-575. (Lecture Notes in Computer Science, Vol. 10116). https://doi.org/10.1007/978-3-319-54407-6_38