On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation

K. R. Anoop; Ramanathan Subramanian; Vassilios Vonikakis; K. R. Ramakrishnan; Stefan Winkler

doi:10.1109/ICIP.2015.7351700

On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation

K. R. Anoop, Ramanathan Subramanian, Vassilios Vonikakis, K. R. Ramakrishnan, Stefan Winkler

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

1 Citation (Scopus)

Abstract

The utility of canonical correlation analysis (CCA) for domain adaptation (DA) in the context of multi-view head pose estimation is examined in this work. We consider the three problems studied in [1], where different DA approaches are explored to transfer head pose-related knowledge from an extensively labeled source dataset to a sparsely labeled target set, whose attributes are vastly different from the source. CCA is found to benefit DA for all the three problems, and the use of a covariance profile-based diagonality score (DS) also improves classification performance with respect to a nearest neighbor (NN) classifier.

Original language	English
Title of host publication	2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
Editors	Jean-Luc Dugelay, Andre Morin
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	4708-4712
Number of pages	5
ISBN (Electronic)	9781479983391
ISBN (Print)	9781479983391
DOIs	https://doi.org/10.1109/ICIP.2015.7351700
Publication status	Published - 9 Dec 2015
Externally published	Yes
Event	IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada Duration: 27 Sept 2015 → 30 Sept 2015

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2015-December

Conference

Conference	IEEE International Conference on Image Processing, ICIP 2015
Country/Territory	Canada
City	Quebec City
Period	27/09/15 → 30/09/15

Access to Document

10.1109/ICIP.2015.7351700

Cite this

Anoop, K. R., Subramanian, R., Vonikakis, V., Ramakrishnan, K. R., & Winkler, S. (2015). On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation. In J-L. Dugelay, & A. Morin (Eds.), 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings (pp. 4708-4712). [7351700] (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICIP.2015.7351700

Anoop, K. R. ; Subramanian, Ramanathan ; Vonikakis, Vassilios et al. / On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation. 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. editor / Jean-Luc Dugelay ; Andre Morin. United States : IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 4708-4712 (Proceedings - International Conference on Image Processing, ICIP).

@inproceedings{6d8a060a56d34ecf9a3170029d03b391,

title = "On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation",

abstract = "The utility of canonical correlation analysis (CCA) for domain adaptation (DA) in the context of multi-view head pose estimation is examined in this work. We consider the three problems studied in [1], where different DA approaches are explored to transfer head pose-related knowledge from an extensively labeled source dataset to a sparsely labeled target set, whose attributes are vastly different from the source. CCA is found to benefit DA for all the three problems, and the use of a covariance profile-based diagonality score (DS) also improves classification performance with respect to a nearest neighbor (NN) classifier.",

keywords = "Canonical Correlation Analysis, Diagonality score, Domain Adaptation, Head pose classification",

author = "Anoop, {K. R.} and Ramanathan Subramanian and Vassilios Vonikakis and Ramakrishnan, {K. R.} and Stefan Winkler",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; IEEE International Conference on Image Processing, ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

year = "2015",

month = dec,

day = "9",

doi = "10.1109/ICIP.2015.7351700",

language = "English",

isbn = "9781479983391",

series = "Proceedings - International Conference on Image Processing, ICIP",

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

pages = "4708--4712",

editor = "Jean-Luc Dugelay and Andre Morin",

booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",

address = "United States",

}

Anoop, KR, Subramanian, R, Vonikakis, V, Ramakrishnan, KR & Winkler, S 2015, On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation. in J-L Dugelay & A Morin (eds), 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings., 7351700, Proceedings - International Conference on Image Processing, ICIP, vol. 2015-December, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 4708-4712, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7351700

On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation. / Anoop, K. R.; Subramanian, Ramanathan; Vonikakis, Vassilios et al.
2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. ed. / Jean-Luc Dugelay; Andre Morin. United States: IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 4708-4712 7351700 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December).

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

TY - GEN

T1 - On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation

AU - Anoop, K. R.

AU - Subramanian, Ramanathan

AU - Vonikakis, Vassilios

AU - Ramakrishnan, K. R.

AU - Winkler, Stefan

PY - 2015/12/9

Y1 - 2015/12/9

N2 - The utility of canonical correlation analysis (CCA) for domain adaptation (DA) in the context of multi-view head pose estimation is examined in this work. We consider the three problems studied in [1], where different DA approaches are explored to transfer head pose-related knowledge from an extensively labeled source dataset to a sparsely labeled target set, whose attributes are vastly different from the source. CCA is found to benefit DA for all the three problems, and the use of a covariance profile-based diagonality score (DS) also improves classification performance with respect to a nearest neighbor (NN) classifier.

AB - The utility of canonical correlation analysis (CCA) for domain adaptation (DA) in the context of multi-view head pose estimation is examined in this work. We consider the three problems studied in [1], where different DA approaches are explored to transfer head pose-related knowledge from an extensively labeled source dataset to a sparsely labeled target set, whose attributes are vastly different from the source. CCA is found to benefit DA for all the three problems, and the use of a covariance profile-based diagonality score (DS) also improves classification performance with respect to a nearest neighbor (NN) classifier.

KW - Canonical Correlation Analysis

KW - Diagonality score

KW - Domain Adaptation

KW - Head pose classification

UR - http://www.scopus.com/inward/record.url?scp=84956673342&partnerID=8YFLogxK

UR - http://www.icip2015.org

UR - https://www.mendeley.com/catalogue/4a4413be-0ca0-3cf9-89fb-b299e4c09c49/

U2 - 10.1109/ICIP.2015.7351700

DO - 10.1109/ICIP.2015.7351700

M3 - Conference contribution

AN - SCOPUS:84956673342

SN - 9781479983391

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 4708

EP - 4712

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

A2 - Dugelay, Jean-Luc

A2 - Morin, Andre

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - IEEE International Conference on Image Processing, ICIP 2015

Y2 - 27 September 2015 through 30 September 2015

ER -

Anoop KR, Subramanian R, Vonikakis V, Ramakrishnan KR, Winkler S. On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation. In Dugelay J-L, Morin A, editors, 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. United States: IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 4708-4712. 7351700. (Proceedings - International Conference on Image Processing, ICIP). doi: 10.1109/ICIP.2015.7351700

On the utility of canonical correlation analysis for domain adaptation in multi-view headpose estimation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this