Finding Happiest Moments in a Social Context

Abhinav Dhall, Jyoti Dhall, Ibrahim Radwan, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

18 Citations (Scopus)
2 Downloads (Pure)

Abstract

We study the problem of expression analysis for a group of people. Automatic facial expression analysis has seen much research in recent times. However, little attention has been given to the estimation of the overall expression theme conveyed by an image of a group of people. Specifically, this work focuses on formulating a framework for happiness intensity estimation for groups based on social context information. The main contributions of this paper are: a) defining automatic frameworks for group expressions; b) social features, which compute weights on expression intensities; c) an automatic face occlusion intensity detection method; and d) an ‘in the wild’ labelled database containing images having multiple subjects from different scenarios. The experiments show that the global and local contexts provide useful information for theme expression analysis, with results similar to human perception results.
Original languageEnglish
Title of host publication11th Asian Conference on Computer Vision
EditorsKyoung Mu Lee, Yasuyuki Matsushita, James M Rehg, Zhanyi Hu
Place of PublicationBerlin Heidelberg
PublisherSpringer
Pages613-626
Number of pages14
Volume7725
ISBN (Print)9783642374432
DOIs
Publication statusPublished - 2013
Event11th Asian Conference on Computer Vision - Daejeon, Daejeon, Korea, Republic of
Duration: 5 Nov 20129 Nov 2012

Conference

Conference11th Asian Conference on Computer Vision
CountryKorea, Republic of
CityDaejeon
Period5/11/129/11/12

Fingerprint

Experiments

Cite this

Dhall, A., Dhall, J., Radwan, I., & Goecke, R. (2013). Finding Happiest Moments in a Social Context. In K. M. Lee, Y. Matsushita, J. M. Rehg, & Z. Hu (Eds.), 11th Asian Conference on Computer Vision (Vol. 7725, pp. 613-626). Berlin Heidelberg: Springer. https://doi.org/10.1007/978-3-642-37444-9_48
Dhall, Abhinav ; Dhall, Jyoti ; Radwan, Ibrahim ; Goecke, Roland. / Finding Happiest Moments in a Social Context. 11th Asian Conference on Computer Vision. editor / Kyoung Mu Lee ; Yasuyuki Matsushita ; James M Rehg ; Zhanyi Hu. Vol. 7725 Berlin Heidelberg : Springer, 2013. pp. 613-626
@inproceedings{af444214681c4ce2af9811c308d0e81b,
title = "Finding Happiest Moments in a Social Context",
abstract = "We study the problem of expression analysis for a group of people. Automatic facial expression analysis has seen much research in recent times. However, little attention has been given to the estimation of the overall expression theme conveyed by an image of a group of people. Specifically, this work focuses on formulating a framework for happiness intensity estimation for groups based on social context information. The main contributions of this paper are: a) defining automatic frameworks for group expressions; b) social features, which compute weights on expression intensities; c) an automatic face occlusion intensity detection method; and d) an ‘in the wild’ labelled database containing images having multiple subjects from different scenarios. The experiments show that the global and local contexts provide useful information for theme expression analysis, with results similar to human perception results.",
keywords = "Affective computing, Context aware modelling, Facial expression analysis",
author = "Abhinav Dhall and Jyoti Dhall and Ibrahim Radwan and Roland Goecke",
year = "2013",
doi = "10.1007/978-3-642-37444-9_48",
language = "English",
isbn = "9783642374432",
volume = "7725",
pages = "613--626",
editor = "Lee, {Kyoung Mu} and Yasuyuki Matsushita and Rehg, {James M} and Zhanyi Hu",
booktitle = "11th Asian Conference on Computer Vision",
publisher = "Springer",
address = "Netherlands",

}

Dhall, A, Dhall, J, Radwan, I & Goecke, R 2013, Finding Happiest Moments in a Social Context. in KM Lee, Y Matsushita, JM Rehg & Z Hu (eds), 11th Asian Conference on Computer Vision. vol. 7725, Springer, Berlin Heidelberg, pp. 613-626, 11th Asian Conference on Computer Vision, Daejeon, Korea, Republic of, 5/11/12. https://doi.org/10.1007/978-3-642-37444-9_48

Finding Happiest Moments in a Social Context. / Dhall, Abhinav; Dhall, Jyoti; Radwan, Ibrahim; Goecke, Roland.

11th Asian Conference on Computer Vision. ed. / Kyoung Mu Lee; Yasuyuki Matsushita; James M Rehg; Zhanyi Hu. Vol. 7725 Berlin Heidelberg : Springer, 2013. p. 613-626.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Finding Happiest Moments in a Social Context

AU - Dhall, Abhinav

AU - Dhall, Jyoti

AU - Radwan, Ibrahim

AU - Goecke, Roland

PY - 2013

Y1 - 2013

N2 - We study the problem of expression analysis for a group of people. Automatic facial expression analysis has seen much research in recent times. However, little attention has been given to the estimation of the overall expression theme conveyed by an image of a group of people. Specifically, this work focuses on formulating a framework for happiness intensity estimation for groups based on social context information. The main contributions of this paper are: a) defining automatic frameworks for group expressions; b) social features, which compute weights on expression intensities; c) an automatic face occlusion intensity detection method; and d) an ‘in the wild’ labelled database containing images having multiple subjects from different scenarios. The experiments show that the global and local contexts provide useful information for theme expression analysis, with results similar to human perception results.

AB - We study the problem of expression analysis for a group of people. Automatic facial expression analysis has seen much research in recent times. However, little attention has been given to the estimation of the overall expression theme conveyed by an image of a group of people. Specifically, this work focuses on formulating a framework for happiness intensity estimation for groups based on social context information. The main contributions of this paper are: a) defining automatic frameworks for group expressions; b) social features, which compute weights on expression intensities; c) an automatic face occlusion intensity detection method; and d) an ‘in the wild’ labelled database containing images having multiple subjects from different scenarios. The experiments show that the global and local contexts provide useful information for theme expression analysis, with results similar to human perception results.

KW - Affective computing

KW - Context aware modelling

KW - Facial expression analysis

U2 - 10.1007/978-3-642-37444-9_48

DO - 10.1007/978-3-642-37444-9_48

M3 - Conference contribution

SN - 9783642374432

VL - 7725

SP - 613

EP - 626

BT - 11th Asian Conference on Computer Vision

A2 - Lee, Kyoung Mu

A2 - Matsushita, Yasuyuki

A2 - Rehg, James M

A2 - Hu, Zhanyi

PB - Springer

CY - Berlin Heidelberg

ER -

Dhall A, Dhall J, Radwan I, Goecke R. Finding Happiest Moments in a Social Context. In Lee KM, Matsushita Y, Rehg JM, Hu Z, editors, 11th Asian Conference on Computer Vision. Vol. 7725. Berlin Heidelberg: Springer. 2013. p. 613-626 https://doi.org/10.1007/978-3-642-37444-9_48