Using a Tensor Framework for the Analysis of Facial Dynamics

Lisa N Gralewski; N Campbell; Ian S Penton-Voak

doi:10.1109/FGR.2006.108

Using a Tensor Framework for the Analysis of Facial Dynamics

Lisa N Gralewski, N Campbell, Ian S Penton-Voak

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

21 Citations (Scopus)

Abstract

Research has shown that the dynamics of facial motion are important in the perception of gender, identity, and emotion. In this paper we show that it is possible to use a multilinear tensor framework to extract facial motion signatures and to cluster these signatures by gender or by emotion. Here we consider only the dynamics of internal features of the face (e.g. eyebrows, eyelids and mouth) so as to remove structural and shape cues to identity and gender. Such structural gender biases include jaw width and forehead shape and their removal ensures dynamic cues alone are being used. Additionally, we demonstrate the generative capabilities of using a tensor framework, by consistently synthesising new motion signatures.

Translated title of the contribution	Using a Tensor Framework for the Analysis of Facial Dynamics
Original language	English
Title of host publication	7th International Conference on Automatic Face and Gesture Recognition (FGR06)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	6
ISBN (Print)	0-7695-2503-2
DOIs	https://doi.org/10.1109/FGR.2006.108
Publication status	Published - 24 Apr 2006

Bibliographical note

Conference Proceedings/Title of Journal: 7th International Conference of Automatic Face and Gesture Recognition, FG2006

Research Groups and Themes

Cognitive Science
Social Cognition

Access to Document

10.1109/FGR.2006.108

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=2000519

Handle.net

Persistent link

Cite this

@inproceedings{d30b19ff9eef48bd831846aa7c3309f7,

title = "Using a Tensor Framework for the Analysis of Facial Dynamics",

abstract = " Research has shown that the dynamics of facial motion are important in the perception of gender, identity, and emotion. In this paper we show that it is possible to use a multilinear tensor framework to extract facial motion signatures and to cluster these signatures by gender or by emotion. Here we consider only the dynamics of internal features of the face (e.g. eyebrows, eyelids and mouth) so as to remove structural and shape cues to identity and gender. Such structural gender biases include jaw width and forehead shape and their removal ensures dynamic cues alone are being used. Additionally, we demonstrate the generative capabilities of using a tensor framework, by consistently synthesising new motion signatures. ",

author = "Gralewski, {Lisa N} and N Campbell and Penton-Voak, {Ian S}",

note = "Conference Proceedings/Title of Journal: 7th International Conference of Automatic Face and Gesture Recognition, FG2006",

year = "2006",

month = apr,

day = "24",

doi = "10.1109/FGR.2006.108",

language = "English",

isbn = "0-7695-2503-2",

booktitle = "7th International Conference on Automatic Face and Gesture Recognition (FGR06)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Using a Tensor Framework for the Analysis of Facial Dynamics. / Gralewski, Lisa N; Campbell, N ; Penton-Voak, Ian S.
7th International Conference on Automatic Face and Gesture Recognition (FGR06). Institute of Electrical and Electronics Engineers (IEEE), 2006.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Using a Tensor Framework for the Analysis of Facial Dynamics

AU - Gralewski, Lisa N

AU - Campbell, N

AU - Penton-Voak, Ian S

N1 - Conference Proceedings/Title of Journal: 7th International Conference of Automatic Face and Gesture Recognition, FG2006

PY - 2006/4/24

Y1 - 2006/4/24

N2 - Research has shown that the dynamics of facial motion are important in the perception of gender, identity, and emotion. In this paper we show that it is possible to use a multilinear tensor framework to extract facial motion signatures and to cluster these signatures by gender or by emotion. Here we consider only the dynamics of internal features of the face (e.g. eyebrows, eyelids and mouth) so as to remove structural and shape cues to identity and gender. Such structural gender biases include jaw width and forehead shape and their removal ensures dynamic cues alone are being used. Additionally, we demonstrate the generative capabilities of using a tensor framework, by consistently synthesising new motion signatures.

AB - Research has shown that the dynamics of facial motion are important in the perception of gender, identity, and emotion. In this paper we show that it is possible to use a multilinear tensor framework to extract facial motion signatures and to cluster these signatures by gender or by emotion. Here we consider only the dynamics of internal features of the face (e.g. eyebrows, eyelids and mouth) so as to remove structural and shape cues to identity and gender. Such structural gender biases include jaw width and forehead shape and their removal ensures dynamic cues alone are being used. Additionally, we demonstrate the generative capabilities of using a tensor framework, by consistently synthesising new motion signatures.

U2 - 10.1109/FGR.2006.108

DO - 10.1109/FGR.2006.108

M3 - Conference Contribution (Conference Proceeding)

SN - 0-7695-2503-2

BT - 7th International Conference on Automatic Face and Gesture Recognition (FGR06)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Using a Tensor Framework for the Analysis of Facial Dynamics

Abstract

Bibliographical note

Research Groups and Themes

Access to Document

Handle.net

Fingerprint

Cite this