Learning the multilinear structure of visual data

Wang, Mengjiao, Panagakis, Yannis ORCID: https://orcid.org/0000-0003-0153-5210, Snape, Patrick and Zafeiriou, Stefanos (2017) Learning the multilinear structure of visual data. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 21-26 Jul 2017, Honolulu, HI, USA. ISBN 9781538604571. ISSN 1063-6919 [Conference or Workshop Item] (doi:10.1109/CVPR.2017.641)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (1MB) | Preview

Abstract

Statistical decomposition methods are of paramount importance in discovering the modes of variations of visual data. Probably the most prominent linear decomposition method is the Principal Component Analysis (PCA), which discovers a single mode of variation in the data. However, in practice, visual data exhibit several modes of variations. For instance, the appearance of faces varies in identity, expression, pose etc. To extract these modes of variations from visual data, several supervised methods, such as the TensorFaces, that rely on multilinear (tensor) decomposition (e.g., Higher Order SVD) have been developed. The main drawbacks of such methods is that they require both labels regarding the modes of variations and the same number of samples under all modes of variations (e.g., the same face under different expressions, poses etc.). Therefore, their applicability is limited to well-organised data, usually captured in well-controlled conditions. In this paper, we propose the first general multilinear method, to the best of our knowledge, that discovers the multilinear structure of visual data in unsupervised setting. That is, without the presence of labels. We demonstrate the applicability of the proposed method in two applications, namely Shape from Shading (SfS) and expression transfer.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 23788
Notes on copyright: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Useful Links:
Depositing User: Yannis Panagakis
Date Deposited: 07 Mar 2018 16:55
Last Modified: 15 Jun 2021 04:28
URI: https://eprints.mdx.ac.uk/id/eprint/23788

Actions (login required)

View Item View Item

Statistics

Downloads
Activity Overview
122Downloads
223Hits

Additional statistics are available via IRStats2.