Bridging face and sound modalities through Domain Adaptation Metric Learning

Christos Athanasiadis; Enrique Hortal; Stelios Asteriadis

Bridging face and sound modalities through Domain Adaptation Metric Learning

Christos Athanasiadis^*, Enrique Hortal, Stelios Asteriadis

^*Corresponding author for this work

Advanced Computing Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

15 Downloads (Pure)

Abstract

Robust emotion recognition systems require extensive training by employing huge number of training samples with purpose of generating sophisticated models. Furthermore, research is mostly focused on facial expression recognition due, mainly to, the wide availability of related datasets. However, the existence of rich and publicly available datasets is not the case for other modalities like sound and so forth. In this work, a heterogeneous domain adaptation framework is introduced for bridging two inherently different domains (namely face and audio). The purpose is to perform affect recognition on the modality where only a small amount of data is available, leveraging large amounts of data from another modality.

Original language	English
Title of host publication	ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 24-26 April 2019
Pages	385-390
ISBN (Electronic)	978-287-587-065-0
Publication status	Published - 2019
Event	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Bruges, Belgium Duration: 24 Apr 2019 → 26 Apr 2019 Conference number: 27

Symposium

Symposium	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Abbreviated title	ESANN 2019
Country/Territory	Belgium
City	Bruges
Period	24/04/19 → 26/04/19

Access to Document

Full text Final published version, 1.47 MBLicence: Taverne

https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-143.pdf

Cite this

Athanasiadis, C., Hortal, E., & Asteriadis, S. (2019). Bridging face and sound modalities through Domain Adaptation Metric Learning. In ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 24-26 April 2019 (pp. 385-390) https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-143.pdf

@inproceedings{7f8dc69b9b12425d96def232f7644851,

title = "Bridging face and sound modalities through Domain Adaptation Metric Learning",

abstract = "Robust emotion recognition systems require extensive training by employing huge number of training samples with purpose of generating sophisticated models. Furthermore, research is mostly focused on facial expression recognition due, mainly to, the wide availability of related datasets. However, the existence of rich and publicly available datasets is not the case for other modalities like sound and so forth. In this work, a heterogeneous domain adaptation framework is introduced for bridging two inherently different domains (namely face and audio). The purpose is to perform affect recognition on the modality where only a small amount of data is available, leveraging large amounts of data from another modality.",

author = "Christos Athanasiadis and Enrique Hortal and Stelios Asteriadis",

note = "Funding Information: ∗This work was totally supported by the Horizon 2020 funded project MaTHiSiS (Managing Affective-learning THrough Intelligent atoms and Smart InteractionS) nr. 687772 (http://www.mathisis-project.eu/). Publisher Copyright: {\textcopyright} 2019 ESANN (i6doc.com). All rights reserved.; European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2019 ; Conference date: 24-04-2019 Through 26-04-2019",

year = "2019",

language = "English",

pages = "385--390",

booktitle = "ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 24-26 April 2019",

}

Athanasiadis, C, Hortal, E & Asteriadis, S 2019, Bridging face and sound modalities through Domain Adaptation Metric Learning. in ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 24-26 April 2019. pp. 385-390, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 24/04/19. <https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-143.pdf>

Bridging face and sound modalities through Domain Adaptation Metric Learning. / Athanasiadis, Christos; Hortal, Enrique ; Asteriadis, Stelios.
ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 24-26 April 2019. 2019. p. 385-390.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Bridging face and sound modalities through Domain Adaptation Metric Learning

AU - Athanasiadis, Christos

AU - Hortal, Enrique

AU - Asteriadis, Stelios

N1 - Conference code: 27

PY - 2019

Y1 - 2019

N2 - Robust emotion recognition systems require extensive training by employing huge number of training samples with purpose of generating sophisticated models. Furthermore, research is mostly focused on facial expression recognition due, mainly to, the wide availability of related datasets. However, the existence of rich and publicly available datasets is not the case for other modalities like sound and so forth. In this work, a heterogeneous domain adaptation framework is introduced for bridging two inherently different domains (namely face and audio). The purpose is to perform affect recognition on the modality where only a small amount of data is available, leveraging large amounts of data from another modality.

AB - Robust emotion recognition systems require extensive training by employing huge number of training samples with purpose of generating sophisticated models. Furthermore, research is mostly focused on facial expression recognition due, mainly to, the wide availability of related datasets. However, the existence of rich and publicly available datasets is not the case for other modalities like sound and so forth. In this work, a heterogeneous domain adaptation framework is introduced for bridging two inherently different domains (namely face and audio). The purpose is to perform affect recognition on the modality where only a small amount of data is available, leveraging large amounts of data from another modality.

M3 - Conference article in proceeding

SP - 385

EP - 390

BT - ESANN 2019 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 24-26 April 2019

T2 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Y2 - 24 April 2019 through 26 April 2019

ER -

Bridging face and sound modalities through Domain Adaptation Metric Learning

Abstract

Symposium

Access to Document

Fingerprint

Cite this