Comparing Interrelationships Between Features and Embedding Methods for Multiple-View Fusion.

Piroddi, Roberta ORCID: 0000-0002-1139-2949, Goulermas, John Yannis, Maskell, Simon ORCID: 0000-0003-1917-2913 and Ralph, Jason F ORCID: 0000-0002-4946-9948 (2018) Comparing Interrelationships Between Features and Embedding Methods for Multiple-View Fusion. In: 21st International Conference on Information Fusion - FUSION 2018, 2018-7-10 - 2018-7-13, Cambridge, U.K..

Text PID5394149_ComparingInterrelationships.pdf - Author Accepted Manuscript Download (21MB)

Abstract

Manifold embedding techniques have properties that render them attractive candidates to learn a compact and general representation of a three dimensional spatial object. In turn this representation can be used for object recognition through classification. This paper presents a comparative study of several supervised spectral embedding techniques and their relationship with the feature space used to describe the exemplars which act as inputs to an embedding procedure. By concentrating on this aspect, we are able to highlight preferential combinations between feature description and embedding, and we formulate recommendations on the use of such methods for fusing multiple views of an object to recognize it under variable poses.

Item Type:	Conference or Workshop Item (Unspecified)
Uncontrolled Keywords:	Manifold embedding, Multiple-view representation learning, Machine learning, Object recognition, Information fusion, View synthesis
Depositing User:	Symplectic Admin
Date Deposited:	12 Jun 2018 09:16
Last Modified:	15 Mar 2024 03:20
DOI:	10.23919/icif.2018.8455547
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3022438