ON THE UTILITY OF CANONICAL CORRELATION ANALYSIS FOR DOMAIN ADAPTATION IN MULTI-VIEW HEADPOSE ESTIMATION

Anoop, KR and Subramanian, Ramanathan and Vonikakis, Vassilios and Ramakrishnan, KR and Winkler, Stefan (2015) ON THE UTILITY OF CANONICAL CORRELATION ANALYSIS FOR DOMAIN ADAPTATION IN MULTI-VIEW HEADPOSE ESTIMATION. In: IEEE International Conference on Image Processing (ICIP), SEP 27-30, 2015, Quebec City, CANADA, pp. 4708-4712.

PDF ICIP_4708_2015.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

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.

Item Type:	Conference Proceedings
Series.:	IEEE International Conference on Image Processing ICIP
Publisher:	IEEE
Additional Information:	Copy right of this article belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Keywords:	Canonical Correlation Analysis; Domain Adaptation; Head pose classification; Diagonality score
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	17 May 2016 07:04
Last Modified:	17 May 2016 07:04
URI:	http://eprints.iisc.ac.in/id/eprint/53851

Actions (login required)

View Item