Learning Active Appearance Models form Image Sequences

Jason Sarigih; Roland Goecke

Learning Active Appearance Models form Image Sequences

Jason Sarigih, Roland Goecke

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

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 language	English
Title of host publication	Proceedings of the HCSNet workshop on the use of Vision in HCI
Editors	Jason Sarigih
Place of Publication	Australia
Publisher	ACS
Pages	51-60
Number of pages	10
Publication status	Published - 2006
Externally published	Yes
Event	VisHCI2006 - Canberra, Australia Duration: 1 Nov 2006 → 3 Nov 2006

Conference

Conference	VisHCI2006
Country/Territory	Australia
City	Canberra
Period	1/11/06 → 3/11/06

Access to Document

https://crpit.scem.westernsydney.edu.au/confpapers/CRPITV56Saragih.pdf

Cite this

@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",

note = "VisHCI2006 ; Conference date: 01-11-2006 Through 03-11-2006",

}

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

T2 - VisHCI2006

Y2 - 1 November 2006 through 3 November 2006

ER -

Learning Active Appearance Models form Image Sequences

Abstract

Conference

Access to Document

Fingerprint

Cite this