Learning Active Appearance Models form Image Sequences

Jason Sarigih, Roland Goecke

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

Abstract

One of the major drawbacks of the Active Appearance Model (AAM) is that it requires a training set
of pseudo-dense correspondences. Most methods for
automatic correspondence finding involve a groupwise
model building process which optimises over all images in the training sequence simultaneously. In this
work, we pose the problem of correspondence finding
as an adaptive template tracking process. We investigate the utility of this approach on an audio-visual
(AV) speech database and show that it can give reasonable results.
Original languageEnglish
Title of host publicationProceedings of the HCSNet workshop on the use of Vision in HCI
EditorsJason Sarigih
Place of PublicationAustralia
PublisherACS
Pages51-60
Number of pages10
Publication statusPublished - 2006
Externally publishedYes
EventVisHCI2006 - Canberra, Australia
Duration: 1 Nov 20063 Nov 2006

Conference

ConferenceVisHCI2006
CountryAustralia
CityCanberra
Period1/11/063/11/06

Fingerprint

Problem-Based Learning

Cite this

Sarigih, J., & Goecke, R. (2006). Learning Active Appearance Models form Image Sequences. In J. Sarigih (Ed.), Proceedings of the HCSNet workshop on the use of Vision in HCI (pp. 51-60). Australia: ACS.
Sarigih, Jason ; Goecke, Roland. / Learning Active Appearance Models form Image Sequences. Proceedings of the HCSNet workshop on the use of Vision in HCI. editor / Jason Sarigih. Australia : ACS, 2006. pp. 51-60
@inproceedings{f1123085b3174c37ac7a4cecee53a52b,
title = "Learning Active Appearance Models form Image Sequences",
abstract = "One of the major drawbacks of the Active Appearance Model (AAM) is that it requires a training setof pseudo-dense correspondences. Most methods forautomatic correspondence finding involve a groupwisemodel building process which optimises over all images in the training sequence simultaneously. In thiswork, we pose the problem of correspondence findingas an adaptive template tracking process. We investigate the utility of this approach on an audio-visual(AV) speech database and show that it can give reasonable results.",
author = "Jason Sarigih and Roland Goecke",
year = "2006",
language = "English",
pages = "51--60",
editor = "Jason Sarigih",
booktitle = "Proceedings of the HCSNet workshop on the use of Vision in HCI",
publisher = "ACS",

}

Sarigih, J & Goecke, R 2006, Learning Active Appearance Models form Image Sequences. in J Sarigih (ed.), Proceedings of the HCSNet workshop on the use of Vision in HCI. ACS, Australia, pp. 51-60, VisHCI2006, Canberra, Australia, 1/11/06.

Learning Active Appearance Models form Image Sequences. / Sarigih, Jason; Goecke, Roland.

Proceedings of the HCSNet workshop on the use of Vision in HCI. ed. / Jason Sarigih. Australia : ACS, 2006. p. 51-60.

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

TY - GEN

T1 - Learning Active Appearance Models form Image Sequences

AU - Sarigih, Jason

AU - Goecke, Roland

PY - 2006

Y1 - 2006

N2 - One of the major drawbacks of the Active Appearance Model (AAM) is that it requires a training setof pseudo-dense correspondences. Most methods forautomatic correspondence finding involve a groupwisemodel building process which optimises over all images in the training sequence simultaneously. In thiswork, we pose the problem of correspondence findingas an adaptive template tracking process. We investigate the utility of this approach on an audio-visual(AV) speech database and show that it can give reasonable results.

AB - One of the major drawbacks of the Active Appearance Model (AAM) is that it requires a training setof pseudo-dense correspondences. Most methods forautomatic correspondence finding involve a groupwisemodel building process which optimises over all images in the training sequence simultaneously. In thiswork, we pose the problem of correspondence findingas an adaptive template tracking process. We investigate the utility of this approach on an audio-visual(AV) speech database and show that it can give reasonable results.

M3 - Conference contribution

SP - 51

EP - 60

BT - Proceedings of the HCSNet workshop on the use of Vision in HCI

A2 - Sarigih, Jason

PB - ACS

CY - Australia

ER -

Sarigih J, Goecke R. Learning Active Appearance Models form Image Sequences. In Sarigih J, editor, Proceedings of the HCSNet workshop on the use of Vision in HCI. Australia: ACS. 2006. p. 51-60