Publication:
Human action recognition with sparse classification and multiple-view learning

Thumbnail Image
Identifiers
URI: https://hdl.handle.net/10016/21416
ISSN: 1468-0394 (online)
ISSN: 0266-4720 (print)
DOI: https://doi.org/10.1111/exsy.12040
UXXI: AR/0000015753
Files
human_ES_2014_ps.pdf (4.1 MB)
Publication date
2014-09
Defense date
Authors
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Wiley
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
Employing multiple camera viewpoints in the recognition of human actions increases performance. This paper presents a feature fusion approach to efficiently combine 2D observations extracted from different camera viewpoints. Multiple-view dimensionality reduction is employed to learn a common parameterization of 2D action descriptors computed for each one of the available viewpoints. Canonical correlation analysis and their variants are employed to obtain such parameterizations. A sparse sequence classifier based on L1 regularization is proposed to avoid the problem of having to choose the proper number of dimensions of the common parameterization. The proposed system is employed in the classification of the Inria Xmas Motion Acquisition Sequences (IXMAS) data set with successful results.
Description
Keywords
Human Action Recognition, Multiple View Learning, L1 regularization
Bibliographic citation
Expert Systems (2014). 31(4), 354-364
Collections
DI - GIAA - Artículos de Revistas