ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Mudunuri, Sivaram Prasad and Biswas, Soma (2016) A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching. In: PATTERN RECOGNITION LETTERS, 71 . pp. 38-44.

[img] PDF
Pat_Rec_Let_71_38_2016.pdf - Published Version
Restricted to Registered users only

Download (981kB) | Request a copy
Official URL: http://dx.doi.org/10.1016/j.patrec.2015.12.003


Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

Item Type: Journal Article
Additional Information: Copy right for this article belongs to the ELSEVIER SCIENCE BV, PO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS
Keywords: Face recognition; Activity recognition; Dictionary learning; Metric learning
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 19 Mar 2016 07:30
Last Modified: 19 Mar 2016 07:30
URI: http://eprints.iisc.ac.in/id/eprint/53407

Actions (login required)

View Item View Item